WO2024058707A1

WO2024058707A1 - Method and system for managing supply chain risk

Info

Publication number: WO2024058707A1
Application number: PCT/SG2022/050659
Authority: WO
Inventors: Lounell Bahoy GUETA; Yusuke KITAJIMA
Original assignee: Hitachi, Ltd.
Priority date: 2022-09-15
Filing date: 2022-09-15
Publication date: 2024-03-21

Abstract

A method of managing supply chain risk is provided. The method includes: providing a plurality of nodes for a supply chain network corresponding to a plurality of supplier entities, respectively, the plurality of nodes being grouped into a plurality of tiers across the supply chain network; determining, for each of the plurality of nodes, an overall risk score associated with the node, the overall risk score being determined based on an internal risk score and one or more shared risk scores associated with the node, whereby the one or more shared risk scores are determined between the node and one or more neighbour nodes, respectively, and based on transaction data associated with one or more supplier entities of the plurality of supplier entities corresponding to the one or more neighbour nodes, respectively, each of the one or more neighbour nodes being located in a tier immediately adjacent to a tier of the plurality of tiers in which the node is located; and forming the supply chain network based on the overall risk scores associated with the plurality of nodes. A corresponding system for managing supply chain risk is also provided.

Description

METHOD AND SYSTEM FOR MANAGING SUPPLY CHAIN RISK

TECHNICAL FIELD

[0001] The present invention generally relates to a method and a system for managing supply chain risk.

BACKGROUND

[0002] Evaluation of supply chain risks is complicated as a risk dynamically changes with respect to its magnitude and/or position in a supply chain. Considering a dynamic risk, for example, evaluating a loan application of a supplier or a buyer that is part of a complex supply chain is a tedious process lest approval on the loan application may result in delayed payments and loan defaults. Furthermore, the risk at a company itself and/or its impact may increase over time that may trigger other risks in the supply chain. For illustrative purpose only, FIGs. 1A and IB depict schematic drawings of a supply chain network at a first time instance (at t = T) and a second time instance (at t = T + A), respectively. For example, as illustrated, a risk may originate from one entity (e.g., a company) as shown in FIG. 1A and spreads to other entities as shown in FIG. IB:

[0003] In addition, the existence of multiple entities (e.g., company Col, company Co2 and company Co3) in a supply chain may make risk analysis and evaluation even more complex as data from these companies may be stored in various different data formats, e.g., for various purposes and managed independently. Moreover, a manual evaluation makes the process tedious and prone to error. For example, a manual evaluation may involve multiple factors or dimensions (e.g., economic, environmental, political, and so on), and thus, such a manual evaluation may require an opinion or insight, which is vulnerable to subjectivity, bias, or blind spot.

[0004] A need therefore exists to provide a method and a system for managing supply chain risk, that seek to overcome, or at least ameliorate, one or more problems associated with conventional methods and systems for managing supply chain risk, and in particular, enhancing or improving efficiency and effectiveness in supply chain management, such as automated system for managing supply chain risk with enhanced efficiency and effectiveness. It is against this background that the present invention has been developed. SUMMARY

[0005] According to a first aspect of the present invention, there is provided a method of managing supply chain risk using at least one processor, the method comprising: providing a plurality of nodes for a supply chain network corresponding to a plurality of supplier entities, respectively, the plurality of nodes being grouped into a plurality of tiers across the supply chain network; determining, for each of the plurality of nodes, an overall risk score associated with the node, the overall risk score being determined based on an internal risk score and one or more shared risk scores associated with the node, wherein the one or more shared risk scores are determined between the node and one or more neighbour nodes, respectively, and based on transaction data associated with one or more supplier entities of the plurality of supplier entities corresponding to the one or more neighbour nodes, respectively, each of the one or more neighbour nodes being located in a tier immediately adjacent to a tier of the plurality of tiers in which the node is located; and forming the supply chain network based on the overall risk scores associated with the plurality of nodes.

[0006] According to a second aspect of the present invention, there is provided a system for managing supply chain risk, the system comprising: at least one memory; and at least one processor communicatively coupled to the at least one memory and configured to: provide a plurality of nodes for a supply chain network corresponding to a plurality of supplier entities, respectively, the plurality of nodes being grouped into a plurality of tiers across the supply chain network; determine, for each of the plurality of nodes, an overall risk score associated with the node, the overall risk score being determined based on an internal risk score and one or more shared risk scores associated with the node, wherein the one or more shared risk scores are determined between the node and one or more neighbour nodes, respectively, and based on transaction data associated with one or more supplier entities of the plurality of supplier entities corresponding to the one or more neighbour nodes, respectively, each of the one or more neighbour nodes being located in a tier immediately adjacent to a tier of the plurality of tiers in which the node is located; and form the supply chain network based on the overall risk scores associated with the plurality of nodes.

[0007] According to a third aspect of the present invention, there is provided a computer program product, embodied in one or more non-transitory computer-readable storage mediums, comprising instructions executable by at least one processor to perform the method of managing supply chain risk according to the above-mentioned first aspect of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Embodiments of the present invention will be better understood and readily apparent to one of ordinary skill in the art from the following written description, by way of example only, and in conjunction with the drawings, in which:

FIGs. 1A and IB depict schematic drawings of a supply chain network at a first time instance (at t = T) and a second time instance (at t = T + A), respectively;

FIG. 2 depicts a schematic flow diagram of a method of managing supply chain risk, according to various embodiments of the present invention;

FIG. 3 depicts a schematic block diagram of a system for managing supply chain risk, according to various embodiments of the present invention;

FIG. 4 depicts a schematic block diagram of an exemplary computer system which may be used to realize or implement the system for managing supply chain risk, according to various embodiments of the present invention;

FIG. 5A depicts a schematic drawing of a conventional method of managing supply chain risk whereby the risk of an entity in a supply chain is evaluated only based on internal data associated with the entity;

FIG. 5B depicts a schematic drawing of a method of managing supply chain risk according to various example embodiments of the present invention whereby the risk of an entity in a supply chain is evaluated not only based on internal data associated with the entity, but also data associated with other entities in the supply chain;

FIG. 6 depicts a schematic drawing of an overview of example interactions between a loan management system and various entities or stakeholders, along with example types of information exchanged therebetween, according to various example embodiments of the present invention;

FIG. 7A depicts a schematic drawing of the loan management system, including example components thereof, according to various example embodiments of the present invention;

FIG. 7B depicts a schematic flow diagram illustrating example interactions and data flow between the loan management system and stakeholders, according to various example embodiments of the present invention; FIGs. 8A to 8D illustrate example parameters of various transaction data, according to various example embodiments of the present invention;

FIG. 9 depicts a schematic drawing of a representation of a supply chain network including nodes and edges, according to various example embodiments of the present invention;

FIG. 10 depicts a table showing example calculated values in the analysis result of transaction data, according to various example embodiments of the present invention;

FIG. 11 depicts a schematic flow diagram of a method of creating or generating a supply chain network, according to various example embodiments of the present invention;

FIGs. 12A and 12B depict schematic drawings illustrating the method of creating or generating a supply chain network shown in FIG. 11, according to various example embodiments of the present invention;

FIG. 13 depicts a schematic drawing illustrating a sub-graph evaluation process (which may also be referred to as a high risk node evaluation process), according to various example embodiments of the present invention;

FIG. 14 depicts a schematic flow diagram of the sub-graph evaluation process, according to various example embodiments of the present invention;

FIG. 15 depicts a schematic flow diagram of a method of managing supply chain risk, according to various example embodiments of the present invention;

FIG. 16 depicts a schematic drawing illustrating risk evaluation with multiple nodes, according to various example embodiments of the present invention; and

FIG. 17 depicts a schematic flow diagram of a method of risk evaluation of a company, according to various example embodiments of the present invention.

DETAILED DESCRIPTION

[0009] Various embodiments of the present invention provide a method and a system for managing supply chain risk. For example, as explained in the background, evaluation or management of supply chain risks is complicated as a risk dynamically changes with respect to its magnitude and/or position in a supply chain. Furthermore, the risk at a company itself and/or its impact may increase over time that may trigger other risks in the supply chain, such as illustrated in FIGs. 1A and IB. In addition, manual evaluation or management of supply chain risk is inefficient and ineffective (e.g., time consuming, tedious and prone to errors). Accordingly, a need therefore exists to provide a method and a system for managing supply chain risk, that seek to overcome, or at least ameliorate, one or more problems associated with conventional methods and systems for managing supply chain risk, and in particular, enhancing or improving efficiency and effectiveness in supply chain management, such as automated system for managing supply chain risk with enhanced efficiency and effectiveness.

[0010] FIG. 2 depicts a schematic flow diagram of a method 200 of managing supply chain risk using at least one processor, according to various embodiments of the present invention. The method 200 comprises: providing (at 202) a plurality of nodes for a supply chain network corresponding to a plurality of supplier entities, respectively, the plurality of nodes being grouped into a plurality of tiers across the supply chain network; determining (at 204), for each of the plurality of nodes, an overall risk score associated with the node, the overall risk score being determined based on an internal risk score and one or more shared risk scores associated with the node, wherein the one or more shared risk scores are determined between the node and one or more neighbour nodes, respectively, and based on transaction data associated with one or more supplier entities of the plurality of supplier entities corresponding to the one or more neighbour nodes, respectively, each of the one or more neighbour nodes being located in a tier immediately adjacent to a tier of the plurality of tiers in which the node is located; and forming (at 206) the supply chain network based on the overall risk scores associated with the plurality of nodes.

[0011] In various embodiments, a supplier entity in a supply chain refers to any entity functioning or operating as a supplier of product(s) and/or service(s) (including a part or a component thereof) in the supply chain, such as but not limited to, a producer/manufacturer, a service provider, a vendor, a warehouse, a transportation company, a distribution center, a retailer, and so on. Accordingly, it will be appreciated by a person skilled in the art that a supplier entity may be, for example, an individual, a company or an organization. It will also be appreciated by a person skilled in the art a supplier entity does not need to solely function or operate as a supplier in the supply chain, as long as the supplier entity at least function or operate in part as a supplier in the supply chain. Accordingly, in a supply chain network (which may also be referred to herein as a supplier network), a plurality of nodes corresponding to a plurality of supplier entities, respectively, may be provided.

[0012] In various embodiments, supply chain risk refers to any risk along a supply chain that may negatively affect the production and/or delivery of a product and/or a service to a consumer or buyer (e.g., an end product and/or service to an end consumer), such as the consumer no longer being able to receive the product and/or service as originally agreed or expected or not in a timely manner (i.e., delay). It will be appreciated by a person skilled in the art that there are a wide range of possible risks in a supply chain, such as but not limited to, supplier delay, supplier bankruptcy, supplier fraud, supplier accident, defective product or deficient service, and so on. Accordingly, it will be appreciated by a person skilled in the art that the present invention is not limited to any particular type(s) of supply chain risk.

[0013] In various embodiments, an internal risk associated with a node refers to risk associated with a supplier entity corresponding to the node originating from the supplier entity, such as but not limited to, financial risk of the supplier entity (e.g., based on its credit rating), operational risk of the supplier entity (e.g., based on its operational (e.g., production) reliability rating), sustainability risk of the supplier entity (e.g., based on its ESG (environmental, social and governance) rating), or a combination thereof. It will be appreciated by a person skilled in the art that there are various types of possible risks originating from a supplier entity and the present invention is not limited to any particular type(s) of risk originating from a supplier entity.

[0014] Accordingly, the method 200 of managing supply chain risk has advantageously been found to enhance or improve efficiency and effectiveness in managing supply chain risk. In particular, by determining an overall risk score for a node that does not only take into account an internal risk associated with the node, but also shared risk(s) between the node and its neighbour node(s), the effects of risk spreading or propagation in a supply chain from one supplier entity to another one or more supplier entities can advantageously be captured (taken into account), resulting in a more accurate and practical risk assessment or evaluation in the supply chain. In addition, such an overall risk score associated with the node is determined automatically based on transaction data. Therefore, the method 200 is able to enhance or improve efficiency and effectiveness in supply chain management, such as managing supply chain risk in an automated and dynamic manner with enhanced efficiency and effectiveness. These advantages or technical effects, and/or other advantages or technical effects, will become more apparent to a person skilled in the art as the method 200 of managing supply chain risk, as well as the corresponding system for managing supply chain risk, is described in more detail according to various embodiments and example embodiments of the present invention.

[0015] In various embodiments, for each of the one or more neighbour nodes, the shared risk score associated with the node between the node and the neighbour node is determined based on a forward risk propagation model if the neighbour node is upstream with respect to the node or a backward risk propagation model if the neighbour node is downstream with respect to the node, wherein the forward risk propagation model and the backward risk propagation model each represents a risk of the neighbour node to the node.

[0016] In various embodiments, the forward risk propagation model and the backward risk propagation model are each based on a risk transferability parameter providing a measure of risk transferability from the neighbour node to the node.

[0017] In various embodiments, the forward risk propagation model and the backward risk propagation model are each further based on a confidence parameter of the node with respect to the neighbour node, the confidence parameter providing a measure of confidence of the node on the neighbour node.

[0018] In various embodiments, the risk transferability parameter and the confidence parameter are determined based on the transaction data associated with the supplier entity corresponding to the neighbour node and/or transaction data associated with the supplier entity corresponding to the node.

[0019] In various embodiments, the above-mentioned providing (at 202) the plurality of nodes for the supply chain network corresponding to the plurality of supplier entities, respectively, is based on transaction data associated with one or more of the plurality of supplier entities and/or based on predetermined supplier entity identity data including entity identity information of one or more of the plurality of supplier entities. For example, the plurality of nodes may all be determined based on transaction data associated with the plurality of supplier entities, the plurality of nodes may all be determined based on predetermined supplier entity identity data including entity identity information of the plurality of supplier entities, or a subset of the plurality of nodes may be determined based on transaction data associated with the corresponding subset of the plurality of supplier entities and a remaining subset of the plurality of nodes may be determined based on predetermined supplier entity identity data including entity identity information of the corresponding remaining subset of the plurality of supplier entities.

[0020] In various embodiments, the transaction data associated with a supplier entity of the plurality of supplier entities relates to a transaction involving the supplier entity and comprises entity identity information, product and/or service information and a status of and/or a rating associated with the transaction.

[0021] In various embodiments, the above-mentioned forming (at 206) the supply chain network comprises determining whether to link a node in a tier of the plurality of tiers with a neighbour node in an immediately adjacent tier of the plurality of tiers based the overall risk score associated with the node in the tier and the overall risk score associated with the neighbour node in the immediately adjacent tier of the plurality of tiers.

[0022] In various embodiments, the node in the tier is linked with the neighbour node in the immediately adjacent tier if the overall risk score associated with the node in the tier and the overall risk score associated with the neighbour node in the immediately adjacent tier of the plurality of tiers satisfy a predetermined risk score condition. In various embodiments, the predetermined risk score condition may be based on a predetermined risk score threshold. For example, in the case of a lower overall risk score meaning lower overall risk, the predetermined risk score condition for a node may be satisfied if the overall risk score associated with the node is lower than (or equal to) the predetermined risk score threshold.

[0023] In various embodiments, the above-mentioned determining whether to link the node in the tier with the neighbour node in the immediately adjacent tier is further based on a tier pool size of the tier if the overall risk score associated with the node in the tier does not satisfy the predetermined risk score condition. For example, the predetermined risk score condition for a node may be not satisfied if the overall risk score associated with the node is higher than the predetermined risk score threshold.

[0024] In various embodiments, the above-mentioned determining whether to link the node in the tier with the neighbour node in the immediately adjacent tier is further based on a relative tier pool size between the tier and the immediately adjacent tier if the overall risk score associated with the node in the tier does not satisfy the predetermined risk score condition. For example, the relative tier pool size between the tier and the immediately adjacent tier may be a ratio between the tier pool size of the tier and the tier pool size of the immediately adjacent tier. [0025] In various embodiments, the method 200 further comprises selecting a supply chain path in the supply chain network based on the overall risk scores associated with the plurality of nodes.

[0026] In various embodiments, the above-mentioned selecting the supply chain path comprises: for each of a plurality of candidate supply chain paths in the supply chain network, determining a path risk score associated with the candidate supply chain path based on the overall risk scores associated with nodes along the candidate supply chain path; and selecting a candidate supply chain path amongst the plurality of candidate supply chain paths as the selected supply chain path, the selected supply chain path having associated therewith the path risk score satisfying a predetermined path risk score condition. For example, the predetermined path risk score condition may be a supply chain path amongst the plurality of candidate supply chain paths having the lowest path risk score or within a predetermined path risk score range.

[0027] FIG. 3 depicts a schematic block diagram of a system 300 for managing supply chain risk, according to various embodiments of the present invention, corresponding to the method 200 of managing supply chain risk as described hereinbefore with reference to FIG. 2 according to various embodiments of the present invention. The system 300 comprises: at least one memory 302; and at least one processor 304 communicatively coupled to the at least one memory 302 and configured to: provide a plurality of nodes for a supply chain network corresponding to a plurality of supplier entities, respectively, the plurality of nodes being grouped into a plurality of tiers across the supply chain network; determine, for each of the plurality of nodes, an overall risk score associated with the node, the overall risk score being determined based on an internal risk score and one or more shared risk scores associated with the node, wherein the one or more shared risk scores are determined between the node and one or more neighbour nodes, respectively, and based on transaction data associated with one or more supplier entities of the plurality of supplier entities corresponding to the one or more neighbour nodes, respectively, each of the one or more neighbour nodes being located in a tier immediately adjacent to a tier of the plurality of tiers in which the node is located; and form the supply chain network based on the overall risk scores associated with the plurality of nodes.

[0028] It will be appreciated by a person skilled in the art that the at least one processor 304 may be configured to perform various functions or operations through set(s) of instructions (e.g., software modules) executable by the at least one processor 304 to perform various functions or operations. Accordingly, as shown in FIG. 3, the system 300 may comprise a node module (or a node circuit) 306 configured to perform the above-mentioned provide a plurality of nodes for a supply chain network corresponding to a plurality of supplier entities, respectively; a risk score determining module (or a risk score determining circuit) 308 configured to perform the above-mentioned determine, for each of the plurality of nodes, an overall risk score associated with the node; and a supply chain network forming module (or a supply chain network forming circuit) 310 configured to perform the above-mentioned form the supply chain network based on the overall risk scores associated with the plurality of nodes. [0029] It will be appreciated by a person skilled in the art that the above-mentioned modules are not necessarily separate modules, and two or more modules may be realized by or implemented as one functional module (e.g., a circuit or a software program) as desired or as appropriate without deviating from the scope of the present invention. For example, two or more of the node module 306, the risk score determining module 308 and the supply chain network forming module 310 may be realized (e.g., compiled together) as one executable software program (e.g., software application or simply referred to as an “app”), which for example may be stored in the at least one memory 302 and executable by the at least one processor 304 to perform various functions/operations as described herein according to various embodiments of the present invention.

[0030] In various embodiments, the system 300 for managing supply chain risk corresponds to the method 200 of managing supply chain risk as described hereinbefore with reference to FIG. 2 according to various embodiments, therefore, various functions or operations configured to be performed by the least one processor 304 may correspond to various steps or operations of the method 300 of managing supply chain risk as described hereinbefore according to various embodiments, and thus need not be repeated with respect to the system 300 for managing supply chain risk for clarity and conciseness. In other words, various embodiments described herein in context of the methods are analogously valid for the corresponding systems, and vice versa.

[0031] For example, in various embodiments, the at least one memory 302 may have stored therein the node module 306, the risk score determining module 308 and/or the supply chain network forming module 310, which respectively correspond to various steps (or operations or functions) of the method 200 of managing supply chain risk as described herein according to various embodiments, which are executable by the at least one processor 304 to perform the corresponding functions or operations as described herein.

[0032] A computing system, a controller, a microcontroller or any other system providing a processing capability may be provided according to various embodiments in the present disclosure. Such a system may be taken to include one or more processors and one or more computer-readable storage mediums. For example, the system 300 for managing supply chain risk described hereinbefore may include at least one processor (or controller) 304 and at least one computer-readable storage medium (or memory) 302 which are for example used in various processing carried out therein as described herein. A memory or computer-readable storage medium used in various embodiments may be a volatile memory, for example a DRAM (Dynamic Random Access Memory) or a non-volatile memory, for example a PROM (Programmable Read Only Memory), an EPROM (Erasable PROM), EEPROM (Electrically Erasable PROM), or a flash memory, e.g., a floating gate memory, a charge trapping memory, an MRAM (Magnetoresistive Random Access Memory) or a PCRAM (Phase Change Random Access Memory). [0033] In various embodiments, a “circuit” may be understood as any kind of a logic implementing entity, which may be special purpose circuitry or a processor executing software stored in a memory, firmware, or any combination thereof. Thus, in an embodiment, a “circuit” may be a hard-wired logic circuit or a programmable logic circuit such as a programmable processor, e.g., a microprocessor (e.g., a Complex Instruction Set Computer (CISC) processor or a Reduced Instruction Set Computer (RISC) processor). A “circuit” may also be a processor executing software, e.g., any kind of computer program, e.g., a computer program using a virtual machine code, e.g., Java. Any other kind of implementation of the respective functions may also be understood as a “circuit” in accordance with various embodiments. Similarly, a “module” may be a portion of a system according to various embodiments and may encompass a “circuit” as described above, or may be understood to be any kind of a logic-implementing entity.

[0034] Some portions of the present disclosure are explicitly or implicitly presented in terms of algorithms and functional or symbolic representations of operations on data within a computer memory. These algorithmic descriptions and functional or symbolic representations are the means used by those skilled in the data processing arts to convey most effectively the substance of their work to others skilled in the art. An algorithm is here, and generally, conceived to be a self-consistent sequence of steps leading to a desired result. The steps are those requiring physical manipulations of physical quantities, such as electrical, magnetic or optical signals capable of being stored, transferred, combined, compared, and otherwise manipulated.

[0035] Unless specifically stated otherwise, and as apparent from the following, it will be appreciated that throughout the present specification, description or discussions utilizing terms such as “providing”, “determining”, “forming”, “selecting” or the like, refer to the actions and processes of a computer system, or similar electronic device, that manipulates and transforms data represented as physical quantities within the computer system into other data similarly represented as physical quantities within the computer system or other information storage, transmission or display devices.

[0036] The present specification also discloses a system (e.g., which may also be embodied as a device or an apparatus), such as the system 300 for managing supply chain risk, for performing various operations/functions of various methods described herein. Such a system may be specially constructed for the required purposes, or may comprise a general purpose computer or other device selectively activated or reconfigured by a computer program stored in the computer. The algorithms presented herein are not inherently related to any particular computer or other apparatus. Various general-purpose machines may be used with computer programs in accordance with the teachings herein. Alternatively, the construction of more specialized apparatus to perform various method steps may be appropriate.

[0037] In addition, the present specification also at least implicitly discloses a computer program or software/functional module, in that it would be apparent to the person skilled in the art that individual steps of various methods described herein may be put into effect by computer code. The computer program is not intended to be limited to any particular programming language and implementation thereof. It will be appreciated that a variety of programming languages and coding thereof may be used to implement the teachings of the disclosure contained herein. Moreover, the computer program is not intended to be limited to any particular control flow. There are many other variants of the computer program, which can use different control flows without departing from the scope of the invention. It will be appreciated by a person skilled in the art that various modules described herein (e.g., the node module 306, the risk score determining module 308 and/or the supply chain network forming module 310) may be software module(s) realized by computer program(s) or set(s) of instructions executable by a computer processor to perform the required functions, or may be hardware module(s) being functional hardware unit(s) designed to perform the required functions. It will also be appreciated that a combination of hardware and software modules may be implemented. [0038] Furthermore, one or more of the steps of a computer program/module or method described herein may be performed in parallel rather than sequentially. Such a computer program may be stored on any computer readable medium. The computer readable medium may include storage devices such as magnetic or optical disks, memory chips, or other storage devices suitable for interfacing with a general purpose computer. The computer program when loaded and executed on such a general-purpose computer effectively results in an apparatus that implements the steps of the methods described herein.

[0039] In various embodiments, there is provided a computer program product, embodied in one or more computer-readable storage mediums (non-transitory computer-readable storage medium(s)), comprising instructions (e.g., the node module 306, the risk score determining module 308 and/or the supply chain network forming module 310) executable by one or more computer processors to perform the method 200 of managing supply chain risk, as described herein with reference to FIG. 2 according to various embodiments. Accordingly, various computer programs or modules described herein may be stored in a computer program product receivable by a system therein, such as the system 300 for managing supply chain risk as shown in FIG. 3, for execution by at least one processor 304 of the system 300 to perform various functions.

[0040] Software or functional modules described herein may also be implemented as hardware modules. More particularly, in the hardware sense, a module is a functional hardware unit designed for use with other components or modules. For example, a module may be implemented using discrete electronic components, or it can form a portion of an entire electronic circuit such as an Application Specific Integrated Circuit (ASIC). Numerous other possibilities exist. Those skilled in the art will appreciate that the software or functional module(s) described herein can also be implemented as a combination of hardware and software modules.

[0041] In various embodiments, the system 300 for managing supply chain risk may be realized by any computer system (e.g., desktop or portable computer system) including at least one processor and at least one memory, such as an example computer system 400 as schematically shown in FIG. 4 as an example only and without limitation. Various methods/steps or functional modules may be implemented as software, such as a computer program being executed within the computer system 400, and instructing the computer system 400 (in particular, one or more processors therein) to conduct various functions or operations as described herein according to various embodiments. The computer system 400 may comprise a system unit 402, input devices such as a keyboard and/or a touchscreen 404 and a mouse 406, and a plurality of output devices such as a display 408. The system unit 402 may be connected to a computer network 412 via a suitable transceiver device 414, to enable access to e.g., the Internet or other network systems such as Local Area Network (LAN) or Wide Area Network (WAN). The system unit 402 may include a processor 418 for executing various instructions, a Random Access Memory (RAM) 420 and a Read Only Memory (ROM) 422. The system unit 402 may further include a number of Input/Output (I/O) interfaces, for example I/O interface 424 to the display device 408 and I/O interface 426 to the keyboard 404. The components of the system unit 402 typically communicate via an interconnected bus 428 and in a manner known to the person skilled in the art.

[0042] It will be appreciated by a person skilled in the art that the terminology used herein is for the purpose of describing various embodiments only and is not intended to be limiting of the present invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

[0043] Any reference to an element or a feature herein using a designation such as “first”, “second” and so forth does not limit the quantity or order of such elements or features, unless stated or the context requires otherwise. For example, such designations may be used herein as a convenient way of distinguishing between two or more elements or instances of an element. Thus, a reference to first and second elements does not necessarily mean that only two elements can be employed, or that the first element must precede the second element. In addition, a phrase referring to “at least one of’ a list of items refers to any single item therein or any combination of two or more items therein.

[0044] In order that the present invention may be readily understood and put into practical effect, various example embodiments of the present invention will be described hereinafter by way of examples only and not limitations. It will be appreciated by a person skilled in the art that the present invention may, however, be embodied in various different forms or configurations and should not be construed as limited to the example embodiments set forth hereinafter. Rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present invention to those skilled in the art.

[0045] In particular, for better understanding of the present invention and without limitation or loss of generality, various example embodiments of the present invention may be described with respect to an example application of a system for managing supply chain risk in loan applications for illustration purposes only, which may also be referred to as a loan management system. However, it will be appreciated by a person skilled in the art that the present invention is not limited to such a particular application, and the method and system for managing supply chain risk may be implemented in other types of applications as desired or as appropriate as long as supply chain risk management is required or desired.

[0046] For example, as explained in the background, evaluation or management of supply chain risks is complicated as a risk dynamically changes with respect to its magnitude and/or position in a supply chain. Furthermore, the risk at a company itself and/or its impact may increase over time that may trigger other risks in the supply chain, such as illustrated in FIGs. 1A and IB. In addition, manual evaluation or management of supply chain risk is inefficient and ineffective (e.g., time consuming, tedious and prone to errors). In addition, the existence of multiple entities (e.g., company Col, company Co2 and company Co3) in a supply chain may make risk analysis and evaluation even more complex as data from these companies may be stored in various different data formats, e.g., for various purposes and managed independently. Moreover, a manual evaluation makes the process tedious and prone to error. For example, a manual evaluation may involve multiple factors or dimensions (e.g., economic, environmental, political, and so on), and thus, such a manual evaluation may require an opinion or insight, which is vulnerable to subjectivity, bias, or blind spot.

[0047] In contrast, various example embodiments provide a system for managing supply chain risk that is configured to evaluate an overall risk of an entity (e.g., company) in a supply chain based on internal data associated with the entity and transaction data associated with other entities (neighbour entities) in the supply chain such that the effects of risk spreading or propagation in a supply chain from one entity to another one or more entities can advantageously be captured, resulting in a more accurate and practical risk assessment or evaluation. In various example embodiments, internal data associated with the entity are utilized to determine risk associated with the entity that originates from the entity, such as but not limited to, financial risk of the supplier entity (e.g., based on its credit rating as internal data), operational risk of the supplier entity (e.g., based on its operational (e.g., production) reliability rating as internal data), sustainability risk of the supplier entity (e.g., based on its ESG (environmental, social and governance) rating as internal data), or a combination thereof.

[0048] As an example illustration, FIG. 5A depicts a schematic drawing of a conventional method of managing supply chain risk whereby the risk of an entity in a supply chain is evaluated only based on internal data associated with the entity, and FIG. 5B depicts a schematic drawing of a method of managing supply chain risk according to various example embodiments of the present invention whereby the risk of an entity in a supply chain is evaluated not only based on internal data associated with the entity (e.g., corresponding to an internal risk associated with the entity), but also transaction data associated with other entities (neighbour entities) in the supply chain (e.g., corresponding to a shared risk between the entity and other entities). Therefore, according to various example embodiments, an overall risk associated with an entity in a supply chain, including internal risk and shared risk(s) associated with the entity, is determined.

[0049] Accordingly, various example embodiments generate a supply chain network (or a supplier network) based on estimating shared risks (or dynamic risks) by analysis of transaction data of entities in the supply chain network. In various example embodiments, transaction data may relate to any transaction performed between entities in the course of operation or business, such as but not limited, financial transaction, shipping transaction, order transaction, and manufacturing transaction. It will be appreciated by a person skilled in the art that a wide range of transactions may be performed between entities in the course of operation or business, and the present invention is not limited to any particular type or category of transactions. In various example embodiments, these point-to-point transactions are stitched together so that the risk evaluation is not only confined to one entity or to the two transacting entities (e.g., buyer and seller) but to all related entities providing service(s) and/or product(s) (including a part thereof) in the supply chain. Furthermore, since transaction data are utilized, specific entities can be evaluated instead of merely evaluating a general category or industry which entities generally belong to.

[0050] Various example embodiments further provide modelling of a shared risk (or dynamic risk) associated with a first entity between a first entity and a second entity based on an internal risk of the second entity (e.g., a second company), a risk transferability factor or parameter providing a measure of risk transmissibility (or transferability) from the second entity to the first entity (e.g., a first company) and a confidence factor or parameter providing a measure of confidence of the first entity on the second entity. Accordingly, in various example embodiments, the risk model is based on shared risks.

[0051] In various example embodiments, a shared risk may be represented as, or determined based on, forward and backward risk diffusion (or propagation) models for evaluating risk diffusion in forward and backward directions (or downstream and upstream directions), for example, despite the single or directional flow of product or service in the supply chain. Accordingly, various example embodiments advantageously model the risk spread in a supply chain network as a diffusion or propagation flow. In various example embodiments, the forward risk propagation model and the backward risk propagation model are each based on the risk transferability parameter and the confidence parameter. Accordingly, the shared risk score associated with a first entity between the first entity and a second entity may be determined based on the internal risk score of the second entity, the risk transferability factor from the second entity to the first entity, and the confidence factor of the first entity on the second entity. Thereafter, the total or overall risk score of the first entity may be determined based on the internal risk score of the first entity and one or more shared risk scores between the first entity and one or more second entities. As an illustrative example, by using this risk model according to various example embodiments of the present invention, loan grants can be decided based on confidence and trust on the quality of transaction data as well as on the supplier network data.

[0052] Various example embodiments further generate a suggested or recommended supply chain path, such as a best or an optimal supply chain path (or route) to minimize risk in a supply chain network. For example, the generated supply chain network enables a selection of path extending not only between a seller and a buyer but also among their connections. In various example embodiments, as different paths may have different risks, the supply chain path with the minimum path risk score may be selected.

[0053] Accordingly, various example embodiments evaluate risk by determining shared risk in a supply chain network by using transaction data. For example, various example embodiments may perform pre-evaluation prior to creating a supply chain network, as well as performing a multi-path analysis to evaluate risks. Accordingly, various example embodiments may provide one or more of the following features:

• Risk assessment by applying supply chain network/model;

• Use transaction data (e.g., manufacturing, logistics or financial data) to generate the structure of the supply chain network;

• Use transaction data to model dynamic risk (or shared risk) in the supply chain network;

• Assessment of risk associated with a node prior to creating/linking the node to the supply chain network;

• Utilization of blockchain technology to enhance data integrity and security; and

• Financing options incorporating sustainability measures.

[0054] An example application of a system for managing supply chain risk in loan applications (loan management system) will now be described according to various example embodiments for illustration purposes only. FIG. 6 depicts a schematic drawing of an overview of example interactions between the loan management system 610 and various entities or stakeholders 620, 630, 640, along with example types of information exchanged therebetween, according to various example embodiments of the present invention. In various example embodiments, a buyer 620 is a consumer of a product and/or service, for example, either as a final consumer (i.e., an end consumer) or a supplier 620 (e.g., supplies and also consumes) that is part of a supply chain. A supplier 620 is a provider of a product and/or service (or a part thereof) in the supply chain. A funding provider 640 is a provider of financial product and/or service, such as a bank or a non-bank company that offers and grants loans. A data provider 630 is a provider of transaction data 631, such as a logistics service provider capable of providing shipping transaction data, an e-commerce company capable of providing sales (or order) transaction data, and a data aggregator of sales transactions capable of providing sales (or order) transaction data.

[0055] In various example embodiments, the loan management system 610 is configured to: generate a supply chain network using transaction data provided by data provider(s) 630; evaluate risk by modelling dynamic risk (or shared risk) of entities (e.g., companies), such as buyer company and/or supplier company 620, including companies that are part of a supply chain; match funding from fund provider(s) 640; and provide loan offers to buyer and/or supplier 620 based on financing options provided by the fund provider(s) 640.

[0056] FIG. 7A depicts a schematic drawing of the loan management system 610, including example components thereof, according to various example embodiments of the present invention. The loan pre-processing module 710 may be configured to detect if a loan applicant exists in a supply chain network (or a supplier network) and whether information about internal and shared risks or transaction data is available for determining or updating an overall risk associated with the loan applicant. For example, in a case whereby no prior determination of the overall risk was made or that the validity of the overall risk determined has expired (e.g., has exceeded one year), the loan pre-processing module 710 may obtain the transaction data required through a data request and processing module 720. The data request and processing module 720 may be configured to send a data request 612 to a data provider 630 and receive the corresponding transaction data 631 from the data provider 630. The network creation module 730 may be configured to process or transform transaction data 631 to a supply chain (SC) data element (e.g., corresponding to a node of a supply chain network) and decide on whether to add or not add (or link) the SC data element in a supply chain network. The risk assessment module 740 may be configured to analyze buyer and supplier data, which include primarily transaction data as well as other information about an entity (e.g., a company) such as entity identity information, year of establishment, type of entity (e.g., nature of business), type of product(s)/service(s) provided and so on. The risk assessment module 740 may be configured to analyze the buyer and supplier data to determine the overall risk score associated with the loan applicant and uses the overall risk score to assess risk of granting a loan to the loan applicant. The loan evaluation module 760 may be configured to process funding information 641 from the fund provider(s) 640, the overall risk score from the risk assessment module 740 and the loan request 621 to suggest or recommend one or more financing options as one or more loan offers 611 amongst multiple financing options 642 in the financing options database 751 obtained from the fund provider(s) 640 via the funding information search module 750. In particular, the funding information search module 750 searches for and receives available financing options 642 from the fund provider(s) 640.

[0057] For better understanding, FIG. 7B depicts a schematic flow diagram illustrating the interactions and data flow between the loan management system 610 and the stakeholders 620, 630, 640, according to various example embodiments of the present invention. For example, the loan request or application 621 may include a loan amount and an expected date of release of the loan. The funding query 752 may include a query on available funding (e.g., current funding and future funding) from the funding providers 640. The funding information 641 may include a loan available amount, a loan available date, a range value of interest and a loan duration. The data request 612 may include information (e.g., parameters) for requesting the transaction data 631 desired by the loan management system 610 from the data provider 630, such as for evaluating risk associated with an entity in the supply chain network 731. In various example embodiments, transaction data 631 includes raw transaction data for analysis for forming the supply chain network 731. The matching loan 613 may be a loan specified in the funding information 641 that matches with the loan application 621. For instance, a match may occur when the applied loan amount and other terms specified in the loan application 621 are within the range of the amount and other terms provided in the funding information 641. Financing options 642 may include loan payment terms. Loans with financing options (i.e., loan offer) 611 may be a matching loan with specified interest and payment terms.

[0058] In various example embodiments, transaction data 631 provides point-to-point link between entities (e.g., companies) and is created from actual operations. This link may function as a basic element of a supply chain network. Accordingly, for example, when the transaction data 631 is captured as it is generated, risk assessment can be performed in real-time and up- to-date, as opposed to conducting assessment using annual or quarterly financial reports.

[0059] In various example embodiments, transaction data 631 may relate to any transaction performed between entities in the course of operation or business and may be obtained from various data sources, such as but not limited to, logistics shipping transactions, e-commerce order transactions, company ledger showing financial transactions and manufacturing transactions (e.g., audits of product quality). In various example embodiments, the transaction data 631 associated with an entity relates to a transaction involving the entity and comprises entity identity information, product and/or service information (product and/or service involved in the transaction) and a status of and/or a rating associated with the transaction (e.g., whether a product and/or service has been successfully delivered or the quality rating of a product and/or service provided). For example, the transaction data 631 may include transacting companies identities, product and/or service information, transaction date, product and/or service value or cost, quality rating and so on. In various example embodiments, transaction data 631 may be obtained from one or more data providers 630 manually or automatically, such as via corresponding Application Programming Interface(s) (API(s)).

[0060] As an illustrative example, FIG 8A illustrates example parameters of financial transaction data 810 according to various example embodiments, such as including a date parameter 811, an account ID parameter 812, a transaction ID parameter 813, a transacting company ID parameter 814, an account type parameter 815, a credit value parameter 816, a payment type parameter 817 (e.g., whether on account or in cash), a transaction detail parameter 818 (e.g., product information, such as product name and number of units) and a status parameter 819 (e.g., completed or delayed).

[0061] As an illustrative example, FIG. 8B illustrates example parameters of shipping transaction data 820 according to various example embodiments, such as including a date parameter 821, a shipping company ID parameter 822, a receiving company parameter 823, a transaction detail parameter (e.g., freight detail, e.g., product information, such as the product name, number of units and their value) 824 and a status parameter 825 (e.g., delivery status). For example, the shipping transaction data 820 may correspond to a bill of lading providing details of a freight from a sending company to a receiving company.

[0062] As an illustrative example, FIG. 8C illustrates example parameters of sales order transaction data 830 according to various example embodiments, such as including a date parameter 831, a vendor ID parameter 832, an order ID parameter 833, a buyer ID parameter 834, a transaction detail parameter 835 (e.g., order detail, e.g., product information, such as the product name and number of units), an order amount parameter 836 and a status parameter 837. For example, the sales order transaction data 830 may correspond to a sales order transaction of a supplier company to a customer company.

[0063] As an illustrative example, FIG. 8D illustrates example parameters of manufacturing transaction data 840 according to various example embodiments, such as including a date parameter 841, an ID parameter 842 of an inspection company that conducts an inspection of a product supplied, an ID parameter 843 of a customer that consumes the product of a supplier, a supplier ID parameter 844, a transaction detail parameter 845 (e.g., inspected product information, such as the product name and the number of units) and a rating parameter 846 (e.g., product quality rating). For example, the manufacturing transaction data 840 may correspond to a manufacturing transaction that provides information of the inspected product by an inspection company, such as production data, and quantity.

[0064] FIG. 9 depicts a schematic drawing of a representation of a supply chain network 900 comprising nodes 910, 920 and edges 930, 940, according to various example embodiments of the present invention. Entities (e.g., companies) are represented as nodes, and their relational connection (e.g., transaction therebetween) is represented as an edge. For example, company information (e.g., company profile, credit risk score, aggregated information) may be stored at, or associated with, a node 910, 920. An edge 930, 940 represents a connection or link between two companies. The arrow direction indicates the flow of product and/or service (e.g., between nodes 910, 920, the arrow in the direction from node 920 to node 910 may indicate the flow of product and/or service supplied by node 920 to node 910 and the arrow in the direction from node 910 to node 920 may indicate the flow of product and/or service returned by node 910 to node 920). In various example embodiments, in implementing or forming the supply chain network 900, transaction data is processed and analyzed. The analyzed result may then be provided as an input parameter to an edge function corresponding to the edge 930, 940 as will be described below.

[0065] In various example embodiments, an edge function represents risk dynamics such as a change in risk intensity and/or risk propagation. A risk origin may also be identified since a risk model according to various example embodiments considers risk propagation in two directions (i.e., forward and backward directions). Accordingly, various example embodiments provide a risk model for shared risk modeled by two edge functions, namely, a forward risk propagation function and a backward risk propagation function. In various example embodiments, the forward risk propagation function may be defined as E(start=Co2 920, end=Col 910), and the backward risk propagation function may be defined as E(start=Col 910, end=Co2 920). In various example embodiments, the forward risk propagation function may be any function configured to represent or model a risk propagation from a second entity to a first entity, whereby the second entity is upstream with respect to the first entity. Similarly, the backward risk propagation function may be any function configured to represent or model a risk propagation from a second entity to a first entity, whereby the second entity is downstream with respect to the first entity. In FIG. 9, for example, node 910 corresponds to company Col (a buyer) and node 920 corresponds to company Co2 (a seller). In this example, with respect to node 910, the forward risk propagation function may correspond to edge 930 while that of the backward risk propagation function may correspond to edge 940. Illustratively, a forward risk propagation is in the same direction as the flow of product and/or service, which may be visually shown. On the other hand, a backward risk propagation is in the opposite direction of the flow of product and/or service, which may not typically be shown visually.

[0066] By way of an example only and without limitations, for illustration purpose, assuming that a supply chain network 900 comprises two companies (e.g., Col 910 and Co2 920) as shown in FIG. 9. In various example embodiments, an internal risk is first evaluated or determined at a company (or internal) level of the two companies. Subsequently, a shared risk between these two companies is evaluated or determined. In evaluating the shared risk, the risk of Col 910 is affected by the risk of Co2 920 and vice versa as a result of the forward and backward risk propagation models. For example, suppose that Col 910 has good internal risk score, but if the effect of the shared risk with Co2 920 is poor, then the overall risk of Col 910 may be evaluated or determined to be poor.

[0067] Accordingly, the edge function E(«) may be modelled as diffusion flows comprising forward and backward risk propagations. In various example embodiments, the forward and backward risk propagations each represents a risk of a neighbour node (e.g., coming from the neighbour node) to a node in question, and may be based on a risk transferability factor providing a measure of risk transferability from the neighbour node to the node and a confidence factor providing a measure of confidence of the node on the neighbour node. By way of examples only and without limitations, the forward risk propagation model or function may be expressed as:

E(start = Co2, end = Col) = (Risk of Co2) x (risk transferability factor from Co2 to Col) x (1 - confidence factor of Col on Co2).

(Equation 1) [0068] Similarly, the backward risk propagation model or function may be expressed as:

E(start = Col, end = Co2) = (Risk of Col) x (risk transferability factor from Col to Co2) x (1 - confidence factor of Co2 on Col).

(Equation 2) [0069] Accordingly, the above-mentioned two risk propagation models may be used in determining the shared risk between two companies. For example, in the case of Col 910, the shared risk with Co2 is the result of evaluation of E(start = Co2, end = Col), which is the forward risk propagation model, while that of Co2 920 is the result of evaluation of E(start = Col, end = Co2), which is the backward propagation flow. For example, if Col 910 is connected to other neighbour nodes (e.g., companies), for each of these other neighbour companies, a shared risk between Col 910 and the other neighbour company is also evaluated in the same or similar manner as that between Col 910 and Co2 920. Accordingly, the selection of forward or backward risk propagation model may depend on the direction on the flow of product or services as illustrated in FIG. 9.

[0070] For example, in the forward risk propagation model of Equation 1, the risk of Co2 920 may be the internal risk of Co2 920 and may be determined based on its credit risk, which for example may be estimated as default probability using financial transaction data associated with Co2 920. The transferability factor from Co2 920 to Col 910 may be a risk transferability parameter providing a measure of risk transferability from Co2 920 to Col 910 (e.g., fractional amount of risk from Co2 920 that is transferred to Col 910), which for example, may be a value between 0 and 1 (inclusive of endpoints). The confidence factor of Col 910 on Co2 920 may be a confidence parameter providing a measure of confidence of Col 910 on Co2 920. In various example embodiments, the confidence factor may be a value between 0 and 1 (inclusive of endpoints) (e.g., determined by Col 910). For example, as can be understood from Equations (1) and (2), in various example embodiments, the confidence factor is inversely related or correlated to risk, that is, the higher the confidence factor, the lower the risk, and vice versa. For example, the confidence factor of Col 910 on Co2 920 may be set based on a reputation of Co2 920 based on previous transactions between Col 910 and Co2 920.

[0071] In various example embodiments, the total or overall risk score of Col 910 may be determined or calculated by combining (e.g., summing) the internal risk score of Col 910 and all the shared risk scores of Col 910 with neighbour entities connected to Col 910 (e.g., neighbour nodes which are nodes located in a tier of the supply chain network immediately adjacent the tier in which Col 910 is located). In the above-mentioned example supply chain network 900 shown in FIG. 9, since there is only one neighbour node, only one shared risk score of Col 910 with Co2 920 may be determined for inclusion in the overall risk score of Col 910.

[0072] In various example embodiments, the risk transferability factor (or parameter) from a second entity (e.g., Co2 920) to a first entity (e.g., Col 910) may be determined based on transaction data. By way of examples only and without limitations, the risk transferability factor from a second entity to a first entity may be determined based on the volume or number of units of parts supplied to the first entity (e.g., the number of parts supplied to the first entity over the total number of parts supplied by the second entity) and/or based on the revenue of the first entity (e.g., the revenue from the first entity over the total revenue of the second entity. For example, financial transactions (e.g., 810 shown in FIG. 8A) of the second entity may be analyzed to determine the revenue value from the credit value parameter (e.g., 816) of the first entity that may be found in transacting company parameter (e.g., 814), as well as that of other companies to calculate total revenues considering payment terms as stated in the payment type parameter (e.g., 817) and the transaction detail parameter (e.g., 818). Similarly, the risk transferability factor based on the number of parts supply can be derived from shipping transactions (e.g., 820 shown in FIG. 8B) of the second entity, by analyzing the freight details (e.g., 824) to calculate the number or equivalent value of products delivered to the first entity, which may be found in the receiving company parameter (e.g., 823), as well as the number of same products delivered to other companies (e.g., also found in 823) considering status in 825 (e.g. if some products were returned). For example, similar logic may be applied with respect to order transactions 830 (e.g., shown in FIG. 8C), manufacturing transactions 840 (e.g., shown in FIG. 8D) or other types of transaction data. It will be appreciated by a person skilled in the art that the risk transferability factor may be determined based on transaction data as appropriate or as desired as long as it provides a measure of risk transferability from the second entity to the first entity. Accordingly, it will be appreciated by a person skilled in the art that the present invention is not limited to the above illustrative examples of determining the risk transferability factor.

[0073] In determining the risk transferability factor, it may be possible that the information from the second entity is not complete (e.g., not all financial transactions are shared by the second entity), and the case may be similar with the first entity or Col or other entities. In such a case, financial transactions from the first entity (as well as other entities that may be connected to the second entity) that involve the second entity, as a supplier, but are not present in the financial transactions of the second entity may be utilized in the determination. For example, this is an advantage of creating a supplier network having the capability of combining information from the first and second entities. In various example embodiments, the risk transferability factor may be determined by first determining a sub-risk transferability factor for each of one or more types of transaction data (e.g., transaction data 810, 820, 830, and/or 840). The risk transferability factor may then be determined based on the sub-risk transferability factors determined for the plurality of types of transaction data, such as by selecting a highest sub-risk transferability factor or averaging the sub-risk transferability factors. [0074] In various example embodiments, the confidence factor (or parameter) of the first entity (e.g., Col 910) on the second entity (e.g., Co2 920) may also be determined based on transaction data. By way of examples only and without limitations, the confidence factor of the first entity on the second entity may be determined based on the impression or reputation of the second entity based on the previous transactions with the first entity. For example, one way to objectively quantify confidence is to analyze certain or selected parameters in transaction data. For example, based on the status parameter (e.g., 825) in shipping transaction (e.g., 820 in FIG. 8B), a ratio between the number of incidents related to the second entity (such as delayed delivery, return due to defects) and the total number of incidents of all suppliers of the first entity may be calculated as a measure of uncertainty for the forward risk propagation. Conversely, the status parameter 837 in order transaction (e.g., 830 in FIG. 8C) may be used in determining the confidence factor for backward risk propagation. For example, calculating the number of cancelled transactions from the first entity compared to the total number of cancelled transactions encountered by the second entity. Similarly, the product quality parameter (e.g., 846) in manufacturing transaction (e.g., 840 in FIG. 8D) may be used to calculate the confidence level. It will be appreciated by a person skilled in the art that the confidence factor may be determined based on transaction data as appropriate or as desired as long as it provides a measure (quantitative measure) of confidence of the first entity on the second entity. Accordingly, it will be appreciated by a person skilled in the art that the present invention is not limited to the above illustrative examples of determining the confidence factor.

[0075] In various example embodiments, the confidence factor may be determined by first determining a sub-confidence factor for each of one or more types of transaction data (e.g., transaction data 810, 820, 830, and/or 840). The confidence factor may then be determined based on the sub-confidence factors determined for the plurality of types of transaction data, such as by selecting a lowest sub-confidence factor or averaging the sub-confidence factors.

[0076] In various example embodiments, the determination or calculation of shared risk scores among entities may be applied in various stages of risk evaluation. For example, it may be performed when evaluating whether a poorly rated entity is to be added in the supply chain network. This corresponds to a stage in the supply chain network creation when a node representing an entity is initially evaluated for screening the entity to ensure that poorly rated entity is not inadvertently added in the supply chain network. Another example stage of performing shared risk evaluation is when evaluating a company risk in a created supply chain network, for example, to determine the best connected supply chain path or route. [0077] In various example embodiments, various data elements in transaction data may be analyzed and processed to be integrated in the supply chain network. As described hereinbefore, it will be appreciated by a person skilled in the art that a wide range of transactions may be performed between entities in the course of operation or business, and the present invention is not limited to any particular type or category of transactions. For example, example transaction data may be customs data or cross-border transactions, sales tax information, domestic sales transaction, payment data for both cross-border and domestic. A data source may also be related to green financing for production and distribution facility and resources, emission, energy usage, or information relevant in providing green loan. Analysis result of transaction data may include information with respect to supply, delivery, supplier diversity, connectivity, and risks. [0078] By way of examples only and without limitation, FIG. 10 depicts a table showing example calculated values in the analysis result of transaction data. Consider for instance a first entity (e.g., Col 910) as a buyer and a second entity (e.g., Co2 920) as a supplier. The growth rate in inventory 1001 value may refer to the rate of change over time (e.g., annual rate) of the supplied products to the first entity from the second entity which may be derived for instance from order transaction (e.g., 830 in FIG. 8C). The return rate on defects 1002 may refer to the number of defects compared to the total number of delivered products, which may be determined from shipping transaction (e.g., 820 in FIG. 8B) based on the status parameter (e.g., 825) over a certain time period (e.g., one year). The lead time may be calculated based on the difference in the date and time information (e.g., in 821) from shipping transaction (e.g., 820 in FIG. 8B) for the shipment delivery and the date and time information (e.g., 831) from the order transaction (e.g., 830 in FIG. 8C) corresponding to the shipping transaction (e.g., 820). The lead time variability 1003 may then be calculated based on the variance, or squared standard deviation, of the lead times of the various shipping and ordering transactions. The inventory volume may be calculated based on the total number of products ordered in order information (e.g., 835) of same products, product shipped in freight details (e.g., 824) of shipping transaction (e.g., 820), or devices purchased in transaction details (e.g., 818) of financial transaction (e.g., 810). The inventory volume variability 1004 may then be determined by calculating the variance of these inventory volumes over a period of time (e.g., one year). The delivery cost variability 1005 may similarly be derived by calculating the variance of delivery costs that are provided in freight details (e.g., 824) of shipping transaction 820 as the total cost of the delivered products from the second entity to the first entity. The number of direct connections 1006 may correspond to the number of suppliers and customer connected to an entity (e.g., the first entity if the overall risk score of the first entity is being determined). The number of direct connections may be measured further as the number of supplier connections and as the number of customer connections. The number of distinct connections 1007 may be determined by considering the location or address of an entity (e.g., at a country level) and comparing it to other location or addresses of neighbour entities directly connected therewith. For example, the existence of connection to upstream supplier 1008 may be a binary value (e.g., yes/no) for indicating whether an entity is connected or not to a supplier. The number of paths from upstream suppliers 1009 may denote the number of possible paths that includes the second entity to reach the first entity. The average number of connecting points from upstream supplier 1010 may be determined by counting the number of companies, which include the second entity, between a company and an upstream supplier for each possible path and averaging these numbers by the number of paths. The number of points away from high-risk companies in upstream (assuming same industry) 1011 may be determined by determining a company that is closest to a company such that the path between the companies includes the second entity, and counting the number of companies in-between. For example, the closest company can be determined by closest path algorithm such as Dijkstra Algorithm, and other graph-based search algorithms with a constraint that the second entity is included since the risk transferability factor considers the second entity. Similarly in 1012, a number of points away from high-risk companied in upstream (different company) may be considered. A safe range such as 1 or 2 tier levels may be considered and the number of high-risk companies may be counted in 1013.

[0079] By way of an example, the calculated values under the Supply category (e.g., 1001 and 1002), as well as those under the Delivery category (e.g., 1003, 1004 and 1005) shown in FIG. 10 may be utilized as input parameters for determining the confidence factor of an entity. For instance, as the number of inventories received from the second entity increases in 1001, and the return rate on defects in 1002 decreases, the confidence factor may also increase. Similarly, if the number of lead time variability 1003, the inventory volume variability 1004 or the delivery cost variability 1005 are decreasing, the confidence factor may also increase. For example, a plurality of these determined confidence factor values may be aggregated by setting appropriate weights to calculate the final confidence factor. In various example embodiments, a heuristic based on a statistical analysis, or a machine learning algorithm may be applied to determine the appropriate weights for the determined confidence factor values.

[0080] By way of an example, the risk transferability factor may be implicitly determined based on the possible paths of a supplier network which are determined based on values under the Diversity, Connectivity and Risk categories shown in FIG. 10. For instance, in indirectly determining the risk transferability from the second entity to the first entity, the number of direct connections 1006, of the first entity and the second entity may be determined to estimate the risk transferability factor, which may be utilized if transaction data between the second entity and the first entity is not available or not reliable. In 1007, the risk transferability is even higher if the first entity and the second entity are at the same region that is affected by certain risks, regardless both are affected as represented by forward and backward risk propagation. For example, the calculated values under Connectivity and Risk categories shown in FIG. 10 may consider not only between the first entity and the second entity but other companies upstream and those with high value of internal risks. In particular, by considering the possible paths in 1011, 1012 and 1013, the risk transferability is inversely proportional to the number of points away in 1011 and 1012, whereas directly proportional to the value in 1013. Similarly, a plurality of these determined risk transferability values may be aggregated by setting appropriate weights to calculate the final transferability factor.

[0081] Accordingly, various parameters shown in FIGs. 8A to 8D are example representative of transaction data 631 which may be analysed. For example, to create the supply chain network, identifications of companies involved in transactions such as 812 and 814 of financial transaction data 810, 822 and 823 of shipping transaction data 820, 832 and 834 of sales order transaction data 830, 843 and 844 of manufacturing transaction data 840 may be extracted and utilized (e.g., to provide corresponding nodes in the supply chain network).

[0082] FIG. 11 depicts a schematic flow diagram of a method 1100 of creating or generating a supply chain network, performed by a system, according to various example embodiments of the present invention. At 1110, the system may create pools of suppliers (i.e., corresponding nodes) 1211 from transaction data or a prepared or predetermined list of suppliers. In this regard, a plurality of nodes for the supply chain network corresponding to a plurality of supplier entities, respectively, may be provided based on transaction data associated with one or more of the plurality of supplier entities and/or based on predetermined supplier entity identity data including entity identity information of one or more of the plurality of supplier entities (e.g., corresponding to the above-mentioned prepared or predetermined list of suppliers). If tier information is known (e.g., which supplier in which tier), this step may be skipped and proceed to 1120. At 1120, the system may cluster suppliers for each tier, that is, group the plurality of suppliers (corresponding nodes) into a plurality of tiers across the supply chain network. The pools for each tier 1221, 1222, 1223 may be made based on tier information such as product and/or service provided by suppliers. For better understanding, FIG. 12A depicts a schematic drawing illustrating the processes at 1100 and 1120. If no information about tiers is known, the suppliers may be grouped based on transaction details, such as based on same or similar products/services supplied in 818, products/services in freight details 824, products/services delivered in order information 835, and inspected product information in 845.

[0083] At 1130, the system may calculate or determine an overall risk score (based on internal and shared risk scores) for each supplier based on transaction data (e.g., financial transaction data, sales order transaction data, and green or sustainability related transaction data). For example, node 1A may be determined to have an excellent overall risk score (e.g., satisfying a predetermined risk score condition) while node IB may be determined to have a poor overall risk score (e.g., does not satisfy the predetermined risk score condition). At 1140, the system may generate a hierarchy or connections of suppliers by using the calculated overall risk scores of each supplier. For example, in various example embodiments, poorly-rated suppliers are not selected to be included (or linked) in the supply chain network at this stage due to being high risk. For better understanding, FIG. 12B depicts a schematic drawing illustrating the processes at 1130 and 1140. For example, at 1140, all possible links may be candidates of the supply chain hierarchy, but certain links (e.g., IB 2E) may be omitted since nodes IB and 2E have poor calculated overall risk scores. In this regard, connecting these nodes in the supply chain network may result in spreading risks in the supply chain network.

[0084] In various example embodiments, for a poorly-rated supplier, a method of further evaluating whether to link the corresponding node to neighbour node(s) in the supply chain network is performed. In this regard, a sub-graph comprising its immediate connection(s) to neighbour nodes may be separately (as well as temporarily) created to evaluate its effect on the supply chain network. Accordingly, the sub-graph evaluation may be used to determine whether to add a poorly rated node, and the sub-graph evaluation may thus also be referred to as a high risk node evaluation process.

[0085] At 1150, the system may suggest candidates of sets of suppliers with priorities as the hierarchy of supply chain (e.g., structure of supply chain and links between suppliers). For example, referring to FIG. 12B, the candidate sets may include: Set 1 (path 1A - 2D - 31), Set 2 (path 1A - 2D - 3F) and Set 3 (path 1A - 2C - 3F) and so on. The candidate criteria may be pre-selected by a user (e.g., customer) from a list of metrics such as financial criteria (e.g., credit score, no default record), environmental criteria (e.g., low carbon emission, utilization of energy efficient resources), social criteria, or a combination of these metrics. [0086] At 1160, in various example embodiments, the user of the system may decide which candidate set to be used (e.g., corresponding to selecting a candidate supply chain path amongst a plurality of candidate supply chain paths as a selected supply chain path). For example, a bank may choose Set 3 as it allows selection of suppliers with higher risk but with higher interest rate. As another example, a selected candidate set may have same rating but different green mark, so greener supplier may be selected or preferred.

[0087] As described hereinbefore, at 1140, a sub-graph evaluation may be performed for a poorly-rated supplier such that the system can evaluate whether to add such a supplier in the supply chain network. For example, the sub-graph evaluation may be performed based on a tier pool size of the tier in which such a poorly-rated supplier is located. In this regard, for example, if there are too few suppliers in a tier pool (e.g., less than a predetermined minimum threshold), there may be added risks of pre-eminent bottlenecks, which may outweigh the effects of adding a poorly-rated supplier in the supplier chain network. By doing so, the system can setup and form a more appropriate supply chain network.

[0088] FIG. 13 depicts a schematic drawing illustrating the sub-graph evaluation process (which may also be referred to as a high risk node evaluation process) according to various example embodiments of the present invention. For example, assume that node 7D is only the supplier in Tier n, even if the number of paths is 12 from Tier n-1 to Tier n+1, it cannot be determined if there is a pre-eminent bottleneck by simply checking the total number of paths. In this regard, various example embodiments analyze a sub-graph and compare tier pool sizes. In various example embodiments, the system may perform the following processes: (1) check the current tier pool size of tier n where a poorly-rated or high risk node (e.g., node 7E) is located, (2) compare the tier pool sizes of tiers n-1 and n (i.e., immediately downstream tier), as well as the tier pool sizes of tiers n+1 and n (i.e., immediately upstream tier). Accordingly, this sub-graph evaluation process is applicable when a company with a poor rating (e.g., node 7E) is considered to be added in order to avoid bottlenecks.

[0089] FIG. 14 depicts a schematic flow diagram of the sub-graph evaluation process (or high risk node evaluation process) 1400 according to various example embodiments of the present invention. The process 1400 may start at Tier 1 and iteratively performed up to Tier nMax-1, where nMax corresponds to the lowest tier (or highest tier number ri). At 1412, the pool size of the tier is compared to a predetermined minimum number of suppliers for each tier (minN), such as 1 being the least minimum number. If it is determined that the pool size of the tier is less than or equal to minN, the node in question may be added or accepted to be linked up in the supply chain network. Otherwise, at 1413 and 1414, it is determined whether the relative tier size of tier n and tier n-1 (e.g., a ratio of tier size of tier n over that of tier n-1) is less than a predetermined value (e.g., 0.5 as an example ideal ratio). In this regard, if it is determined that the relative tier size of tiers n and n-1 is less than the predetermined value, which means that the number of companies in tier n-1 is significantly more than that of tier n, the node in question may be added or accepted to be linked up in the supply chain network to avoid bottleneck as a result of fewer number of suppliers in tier n. Otherwise, at 1415 and 1416, it is determined whether the relative tier size of tier n and tier n+1 (e.g., a ratio of tier size of tier n over that of tier n+1) is less than a predetermined value (e.g., 0.5 as an example ideal ratio). In this regard, if it is determined that the relative tier size of tiers n and n+1 is less than the predetermined value, the node in question may be added or accepted to be linked up in the supply chain network. Otherwise, at 1417, the node in question is not added or accepted to be linked up in the supply chain network.

[0090] In various example embodiments, as described hereinbefore, the system for generating a supply chain network as described with reference to FIG. 11 is configured to process transaction data, provide nodes, determine risk scores, and form a supply chain network. As risks are commonly present in a supply chain, various factors that may be internal or external to a supplier entity may cause these risks at different time periods. These risks may impact the supply chain network, for example, various supplier entities may be negatively impacted resulting to shut down or being out of business. In various example embodiments, at an updating phase, the system is configured to continuously receive transaction data and/or supplier entity identity data including entity identity information of one or more supplier entities. If an existing supplier entity (or corresponding node) in the supply chain network, for instance, is a going concern, or as a result of determining its overall risk score has undesirable business performance from having a good rating to a poor rating, such a supplier entity (or corresponding node) may be removed as part of the supply chain network. If so, any edges connected to this supplier entity (or corresponding node) is also correspondingly removed and the overall risk scores of neighbour nodes (in an immediately adjacent tier) are updated. On the other hand, a new supplier entity (or corresponding node) may be added in the supply chain network, for instance as a result of processing transaction data and determining that this new supplier entity has a good overall risk score. In various example embodiments, an update on the internal risk score of a supplier entity or new transaction data between entities in the supply chain network may change the supply chain network. In this regard, in various example embodiments, whenever an update on the internal risk score of a supplier entity or new transaction data is received, the system may determine the overall risk of each supplier entity in the supply chain network and form an updated supply chain network.

[0091] FIG. 15 depicts a schematic flow diagram of a method 1500 of managing supply chain risk, according to various example embodiments of the present invention. For example, the flow diagram summarizes an entire process including: at 1550, analysing the transaction data (e.g., financial data) from a company internally; at 1551, analysing the transaction data to determine the transacting customers and suppliers; at 1552, estimating the internal risk and shared risk; at 1553, generating the supply chain network; at 1554, applying risk score from the supply chain network to find a match, such as for matching loan applications with a fund provider.

[0092] FIG. 16 depicts a schematic drawing illustrating risk evaluation with multiple nodes, according to various example embodiments of the present invention. As shown, the risk score of nodes 2D and 3F have changed after considering shared risks contributed by neighbour or connecting nodes, such as node 2C affecting node 3F, and node 3H affecting node 2D.

[0093] FIG. 17 depicts a schematic flow diagram of a method 1700 of risk evaluation of a company, according to various example embodiments of the present invention. At 1731, an internal risk is first evaluated at a company level based on internal financial, operational, sustainability-related risks associated with the company. At 1732, for each neighbour company (at an immediately adjacent tier), the shared risk between the company and the neighbour company is evaluated based on forward and backward risk propagation models as described hereinbefore according to various example embodiments. For example, the shared risk associated with the company between the company and the neighbour company is evaluated based on the internal risk of the neighbour company and the risk coming from the neighbour company to the company. For example, in FIG. 16, the shared risks associated with node 2D are evaluated by considering the pairings of node 2D with neighbour nodes 3F, 3H, and 31, respectively, as forward propagation, and the pairing of node 2D with neighbour node 1A as backward propagation. Similar evaluation may be conducted for determining the shared risks associated with node 2C by considering the pairs of node 2C with neighbour nodes 3F, 3H and 1A, respectively. For example, node 3F and node 2D have good internal risk scores as shown in FIG. 16 before being updated with shared risks. However, because of the effect of shared risks according to various example embodiments, as shown in FIG. 16 after being updated with shared risks, these nodes are evaluated to have poor overall or total risk scores. This demonstrates the effect of risk propagation, such as node 3H impacting node 2D and in turn, nodes 2C and 2D impacting node 3F. As another example, assume that at a first time instance (e.g., at t = tO), the internal risk of node 2D is good but the overall risk associated with node 2D is poor due to the impact of shared risk(s). At a second time instance (e.g., at t = tl), subsequent to the first time instance, the internal risk of node 2D may have become poor (e.g., their financial performance may have been negatively impacted due to the previous poor overall risk). In such a case, for example, the overall risk of node 2D may still be poor even if the shared risk(s) improves (e.g., become good).

[0094] In some cases, a company requires more than one supplier as it requires higher volume or for some reasons to diversify. In this case, multiple paths can be simultaneously evaluated and ordered based on the total or overall risk scores. Those paths belonging to a band with lower total or overall risk scores are selected.

[0095] In various example embodiments, after the shared risks are evaluated or taken into account, at 1733, the overall risk scores may be aggregated across multiple nodes along a supply chain path. For example, if a buyer evaluates the risk of buying product from entity 1A, a plurality of candidate supply chain paths may be evaluated. For example, with reference to FIG. 16, a path from 3I-^2D- 1 A Buyer may be one candidate supply chain path, and another candidate supply chain path may be 3H- 2C-^lA- Buyer. With multiple candidate supply chain paths, for each candidate supply chain path, the path risk score for the candidate supply chain path can be determined by first aggregating the overall risk scores of each company (or node) in the candidate supply chain path. For example, the aggregation may be performed by adding the overall risk scores at each node in a candidate supply chain path with or without weights at one or more nodes. For example, at 1734, the candidate supply chain path with the minimum risk score may be selected.

[0096] Accordingly, various example embodiments provide a supply chain network management method comprising: analyzing transaction data from companies such as banks, logistics service provider, e-commerce to identify suppliers, customers, products and transaction types; estimating internal risk of suppliers and customers and shared risk between the suppliers and customers using the result from transaction data analysis; and generating a supply chain network based on the estimated risks.

[0097] In various example embodiments, a method for estimating shared risk is provided by evaluating the transmissibility of the internal risk of a second company to a first company, and evaluating the confidence factor of the first company on the second company. [0098] In various example embodiments, a method for selecting supplier is provided by evaluating risks by evaluating multiple paths in supplier network, aggregating the internal and shared risks.

[0099] Accordingly, the method and system for managing supply chain risk according to various example embodiments of the present invention can advantageously provide enhancement for sourcing and procurement solutions. For example, transaction data gathered may be analyzed as described hereinbefore, and an engine may be provided to evaluate suppliers by taking into consideration not just the financial aspect but also other factors such as operation data and compliance requirements. With the method and system for managing supply chain risk according to various example embodiments of the present invention, for example, higher degree of confidence and success rate to find suppliers and partners that match the specifications of a buyer can be found. Consequently, for example in financial applications, financing decisions made by the financial providers can be more accurate by avoiding risks in a supply chain network.

[00100] While embodiments of the invention have been particularly shown and described with reference to specific embodiments, it should be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the scope of the invention as defined by the appended claims. The scope of the invention is thus indicated by the appended claims and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced.

Claims

CLAIMS What is claimed is:

1. A method of managing supply chain risk using at least one processor, the method comprising: providing a plurality of nodes for a supply chain network corresponding to a plurality of supplier entities, respectively, the plurality of nodes being grouped into a plurality of tiers across the supply chain network; determining, for each of the plurality of nodes, an overall risk score associated with the node, the overall risk score being determined based on an internal risk score and one or more shared risk scores associated with the node, wherein the one or more shared risk scores are determined between the node and one or more neighbour nodes, respectively, and based on transaction data associated with one or more supplier entities of the plurality of supplier entities corresponding to the one or more neighbour nodes, respectively, each of the one or more neighbour nodes being located in a tier immediately adjacent to a tier of the plurality of tiers in which the node is located; and forming the supply chain network based on the overall risk scores associated with the plurality of nodes.

2. The method according to claim 1, wherein for each of the one or more neighbour nodes, the shared risk score associated with the node between the node and the neighbour node is determined based on a forward risk propagation model if the neighbour node is upstream with respect to the node or a backward risk propagation model if the neighbour node is downstream with respect to the node, wherein the forward risk propagation model and the backward risk propagation model each represents a risk of the neighbour node to the node.

3. The method according to claim 2, wherein the forward risk propagation model and the backward risk propagation model are each based on a risk transferability parameter providing a measure of risk transferability from the neighbour node to the node.

4. The method according to claim 3, wherein the forward risk propagation model and the backward risk propagation model are each further based on a confidence parameter of the node with respect to the neighbour node, the confidence parameter providing a measure of confidence of the node on the neighbour node.

5. The method according to claim 4, wherein the risk transferability parameter and the confidence parameter are determined based on the transaction data associated with the supplier entity corresponding to the neighbour node and/or transaction data associated with the supplier entity corresponding to the node.

6. The method according to any one of claims 1 to 5, wherein said providing the plurality of nodes for the supply chain network corresponding to the plurality of supplier entities, respectively, is based on transaction data associated with one or more of the plurality of supplier entities and/or based on predetermined supplier entity identity data including entity identity information of one or more of the plurality of supplier entities.

7. The method according to any one of claims 1 to 6, wherein the transaction data associated with a supplier entity of the plurality of supplier entities relates to a transaction involving the supplier entity and comprises entity identity information, product and/or service information and a status of and/or a rating associated with the transaction.

8. The method according to any one of claims 1 to 7, wherein said forming the supply chain network comprises determining whether to link a node in a tier of the plurality of tiers with a neighbour node in an immediately adjacent tier of the plurality of tiers based the overall risk score associated with the node in the tier and the overall risk score associated with the neighbour node in the immediately adjacent tier of the plurality of tiers.

9. The method according to claim 8, wherein the node in the tier is linked with the neighbour node in the immediately adjacent tier if the overall risk score associated with the node in the tier and the overall risk score associated with the neighbour node in the immediately adjacent tier of the plurality of tiers satisfy a predetermined risk score condition.

10. The method according to claim 9, wherein said determining whether to link the node in the tier with the neighbour node in the immediately adjacent tier is further based on a tier pool size of the tier if the overall risk score associated with the node in the tier does not satisfy the predetermined risk score condition.

11. The method according to claim 10, wherein said determining whether to link the node in the tier with the neighbour node in the immediately adjacent tier is further based on a relative tier pool size between the tier and the immediately adjacent tier if the overall risk score associated with the node in the tier does not satisfy the predetermined risk score condition.

12. The method according to any one of claims 1 to 11, further comprising selecting a supply chain path in the supply chain network based on the overall risk scores associated with the plurality of nodes.

13. The method according to claim 12, wherein said selecting the supply chain path comprises: for each of a plurality of candidate supply chain paths in the supply chain network, determining a path risk score associated with the candidate supply chain path based on the overall risk scores associated with nodes along the candidate supply chain path; and selecting a candidate supply chain path amongst the plurality of candidate supply chain paths as the selected supply chain path, the selected supply chain path having associated therewith the path risk score satisfying a predetermined path risk score condition.

14. A system for managing supply chain risk, the system comprising: at least one memory; and at least one processor communicatively coupled to the at least one memory and configured to: provide a plurality of nodes for a supply chain network corresponding to a plurality of supplier entities, respectively, the plurality of nodes being grouped into a plurality of tiers across the supply chain network; determine, for each of the plurality of nodes, an overall risk score associated with the node, the overall risk score being determined based on an internal risk score and one or more shared risk scores associated with the node, wherein the one or more shared risk scores are determined between the node and one or more neighbour nodes, respectively, and based on transaction data associated with one or more supplier entities of the plurality of supplier entities corresponding to the one or more neighbour nodes, respectively, each of the one or more neighbour nodes being located in a tier immediately adjacent to a tier of the plurality of tiers in which the node is located; and form the supply chain network based on the overall risk scores associated with the plurality of nodes.

15. The system according to claim 14, wherein for each of the one or more neighbour nodes, the shared risk score associated with the node between the node and the neighbour node is determined based on a forward risk propagation model if the neighbour node is upstream with respect to the node or a backward risk propagation model if the neighbour node is downstream with respect to the node, wherein the forward risk propagation model and the backward risk propagation model each represents a risk of the neighbour node to the node.

16. The system according to claim 15, wherein the forward risk propagation model and the backward risk propagation model are each based on a risk transferability parameter providing a measure of risk transferability from the neighbour node to the node.

17. The system according to claim 16, wherein the forward risk propagation model and the backward risk propagation model are each further based on a confidence parameter of the node with respect to the neighbour node, the confidence parameter providing a measure of confidence of the node on the neighbour node.

18. The system according to claim 17, wherein the risk transferability parameter and the confidence parameter are determined based on the transaction data associated with the supplier entity corresponding to the neighbour node and/or transaction data associated with the supplier entity corresponding to the node.

19. The system according to any one of claims 14 to 18, wherein said provide the plurality of nodes for the supply chain network corresponding to the plurality of supplier entities, respectively, is based on transaction data associated with one or more of the plurality of supplier entities and/or based on predetermined supplier entity identity data including entity identity information of one or more of the plurality of supplier entities.

20. The system according to any one of claims 14 to 19, wherein the transaction data associated with a supplier entity of the plurality of supplier entities relates to a transaction involving the supplier entity and comprises entity identity information, product and/or service information and a status of and/or a rating associated with the transaction.

21. The system according to any one of claims 14 to 20, wherein said form the supply chain network comprises determining whether to link a node in a tier of the plurality of tiers with a neighbour node in an immediately adjacent tier of the plurality of tiers based the overall risk score associated with the node in the tier and the overall risk score associated with the neighbour node in the immediately adjacent tier of the plurality of tiers.

22. The system according to claim 21, wherein the node in the tier is linked with the neighbour node in the immediately adjacent tier if the overall risk score associated with the node in the tier and the overall risk score associated with the neighbour node in the immediately adjacent tier of the plurality of tiers satisfy a predetermined risk score condition.

23. The system according to claim 22, wherein said determining whether to link the node in the tier with the neighbour node in the immediately adjacent tier is further based on a tier pool size of the tier if the overall risk score associated with the node in the tier does not satisfy the predetermined risk score condition.

24. The system according to claim 23, wherein said determining whether to link the node in the tier with the neighbour node in the immediately adjacent tier is further based on a relative tier pool size between the tier and the immediately adjacent tier if the overall risk score associated with the node in the tier does not satisfy the predetermined risk score condition.

25. The system according to any one of claims 14 to 24, wherein the at least one processor is further configured to select a supply chain path in the supply chain network based on the overall risk scores associated with the plurality of nodes.

26. The system according to claim 25, wherein said select the supply chain path comprises: for each of a plurality of candidate supply chain paths in the supply chain network, determining a path risk score associated with the candidate supply chain path based on the overall risk scores associated with nodes along the candidate supply chain path; and selecting a candidate supply chain path amongst the plurality of candidate supply chain paths as the selected supply chain path, the selected supply chain path having associated therewith the path risk score satisfying a predetermined path risk score condition.