WO2023033708A1 - Procédé d'évaluation de risque de crédit d'une société et plateforme de financement de chaîne d'approvisionnement hébergée sur un réseau de chaîne de blocs - Google Patents

Procédé d'évaluation de risque de crédit d'une société et plateforme de financement de chaîne d'approvisionnement hébergée sur un réseau de chaîne de blocs Download PDF

Info

Publication number
WO2023033708A1
WO2023033708A1 PCT/SG2021/050525 SG2021050525W WO2023033708A1 WO 2023033708 A1 WO2023033708 A1 WO 2023033708A1 SG 2021050525 W SG2021050525 W SG 2021050525W WO 2023033708 A1 WO2023033708 A1 WO 2023033708A1
Authority
WO
WIPO (PCT)
Prior art keywords
supply chain
data
parameter
hash value
input data
Prior art date
Application number
PCT/SG2021/050525
Other languages
English (en)
Inventor
Rajat Goswami PATIT PABAN GOSWAMI
Toshiki Ishii
Yusuke KITAJIMA
Original Assignee
Hitachi, Ltd.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi, Ltd. filed Critical Hitachi, Ltd.
Priority to PCT/SG2021/050525 priority Critical patent/WO2023033708A1/fr
Publication of WO2023033708A1 publication Critical patent/WO2023033708A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/22—Payment schemes or models
    • G06Q20/24—Credit schemes, i.e. "pay after"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/02—Banking, e.g. interest calculation or account maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/03—Credit; Loans; Processing thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/06—Asset management; Financial planning or analysis
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/50—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols using hash chains, e.g. blockchains or hash trees
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L2209/00—Additional information or applications relating to cryptographic mechanisms or cryptographic arrangements for secret or secure communication H04L9/00
    • H04L2209/56—Financial cryptography, e.g. electronic payment or e-cash

Definitions

  • Various embodiments relate to methods of assessing credit risk of a company, and supply chain platforms hosted on a blockchain network.
  • SMEs small medium enterprises
  • issuing small bank loans to the SMEs may be a relatively unattractive business as compared to issuing large bank loans, given the amount of man effort that may be required to conduct the necessary credit risk evaluation compared to the profits that may be made.
  • SMEs are turning to supply chain finance platforms to obtain their loans. These supply chain finance platforms typically calculate credit risk using available platform data relating to transactions, and financial data obtained from financial institutions. As the financial institutions may have limited financial data on SMEs, it may still be challenging to perform the credit risk assessment accurately. Also, on these supply chain finance platforms, the transaction data generally lies with the platform owner, and hence, may be prone to manipulations or bias towards certain suppliers. As such, there is a need for an alternative and trusted form of credit assessment.
  • a method of assessing credit risk of a company may include determining a plurality of parameters based on input data about the company. The method may further include adjusting a predefined weightage for each parameter of the plurality of parameters, based on a quantity of data points in the input data that relates to the respective parameter. The method may further include computing a credit risk score based on the plurality of parameters and their respective adjusted weightages.
  • a non-transitory computer readable medium comprising instructions executable by at least one processor, to perform a method of assessing credit risk of a company.
  • the method of assessing the credit risk of the company may include determining a plurality of parameters based on input data about the company, adjusting a predefined weightage for each parameter of the plurality of parameters based on a quantity of data points in the input data that relates to the respective parameter, and computing a credit risk score based on the plurality of parameters and their respective adjusted weightages.
  • a supply chain platform hosted on a blockchain network.
  • the supply chain platform may include a private ledger configured to store supply chain data of a company.
  • the supply chain platform may further include a smart contract configured to read the supply chain data from the private ledger.
  • the smart contract may be further configured to compute a first parameter based on the supply chain data, and a hash value based on the supply chain data.
  • the supply chain platform may further include a public ledger, wherein the smart contract is further configured to write the first parameter and the hash value to the public ledger.
  • FIG. 1 shows a conceptual diagram of a system for assessing credit risk of a company, according to various embodiments.
  • FIG. 2 shows a conceptual hardware diagram of the system according to various embodiments.
  • FIG. 3 shows a schematic diagram of a supply chain financing platform according to various embodiments.
  • FIG. 4A shows a flowchart of a method of assessing credit risk according to various embodiments.
  • FIG. 4B shows a flowchart of a method of assessing credit risk according to various embodiments.
  • FIG. 5 shows a formula that represents the weightage determination logic of the weight adjustment module, according to various embodiments.
  • FIG. 6 shows a table that lists examples of the inputs and outputs of the segregator engine, according to various embodiments.
  • FIG. 7 shows examples of the table structures of data extracted from the audited statements by the segregator engine, according to various embodiments.
  • Coupled may be understood as electrically coupled or as mechanically coupled, for example attached or fixed, or just in contact without any fixation, and it will be understood that both direct coupling or indirect coupling (in other words: coupling without direct contact) may be provided.
  • a method of assessing credit risk of a company may be provided.
  • the company may also be referred herein as a supplier, as each company may be a supplier connected to a supply chain financing (SCF) platform.
  • the method may include computing a credit risk score using input data that includes financial data, supply chain platform data and an asset trust score.
  • the method may include applying weightages to the components of the input data to compute the credit risk score.
  • the method may further include dynamically adjusting the weightages based on availability of the components of the input data, using a data enhancer module.
  • the data enhancer module may fine tune and penalize the scoring algorithm based on data availability.
  • the method may further include applying machine learning to adjust the weightages.
  • a supply chain platform may be provided.
  • the supply chain platform may be hosted on a blockchain network.
  • the supply chain platform may utilize decentralization technology provided by the blockchain network, to compute and store trusted scores, for example, the asset trust scores.
  • Banks may make their decisions to offer loans, based on these trusted scores. As these trusted scores are computed by the blockchain network and stored in the blockchain, these trusted scores cannot be manipulated and therefore, may be relied upon in the decision making process.
  • Banks may verify the information submitted by the loan applicants based on the hash values stored in the blockchain.
  • the trusted scores may be indicative of the loan applicants’ abilities to repay the debts, and therefore, may also act as digital collateral for the banks.
  • FIG. 1 shows a conceptual diagram of a system 100 for assessing credit risk of a company, according to various embodiments.
  • the system 100 may include a supply chain financing (SCF) platform 200.
  • the SCF platform 200 may be hosted on a computing platform, such as a web-based platform, or a cloud-based platform.
  • the SCF platform 200 may be accessible over a network 110.
  • a credit request user also referred herein as a loan applicant, may request for a loan through the system 100.
  • the loan applicant may be a company, and may be a supplier, that uses the SCF platform 200 to perform transactions, such as purchase and sales of its supplies and products.
  • the SCF platform 200 may store information including supplier profile 104, asset trust score 106, and transaction data 108.
  • the supplier profile 104 may include company profiles of a plurality of suppliers.
  • the SCF platform 200 may store information on the quality control data of the suppliers.
  • the asset trust score may be a trusted score that is computed based on inventory and account receivable information.
  • the transaction data 108 may include information on transaction frequency, order size, supplier rating, and past credit performance.
  • the loan applicant may upload audited statements 102 to the SCF platform 200, through a segregator engine 112.
  • the audited statements 102 may include financial statements, including at least one of balance sheet, cash flow statement and income statement.
  • the balance sheet may include information on assets and liabilities.
  • the cash flow statement may include information on cash flow from operations, investing and financing activities.
  • the income statement may include information related to revenue and expenses. Examples of the data contained in the balance sheet, the cash flow statement and the income statement are shown in FIG. 7.
  • the segregator engine 112 may be configured to calculate financial ratios 132 based on the uploaded audited statements 102. Different companies may use different terminology in their respective financial statements.
  • the relevant data for calculating the financial ratios 132 may be embedded in richly formatted data, such as a combination of textual, structural, tabular formats in business reports.
  • the segregator engine 112 may be further configured to recognize the variations in terminology in the uploaded audited statements 102, and may be configured to extract relevant data from the uploaded audited statements 102.
  • the segregator engine 112 may use a natural language processing tool or, for example, Fonduer, to extract the relevant data.
  • the relevant data may relate to the liquidity, profitability, and solvency of the company.
  • the financial ratios 132 computed by the segregator engine 112 may include, for example, debt to equity ratio, debt to total asset ratio, net profit margin, return on assets, current ratio, quick ratio, etc.
  • the system 100 may further include a dynamic credit scoring (DCS) module 114.
  • the DCS module 114 may extract information from the SCF platform 200.
  • the extracted information may include normalized data from the supplier profile 104 and the transaction data 108.
  • the extracted information may also include the asset trust score 106.
  • the DCS module 114 may also receive financial ratios 132 from the segregator engine 112.
  • the DCS module 114 may generate a credit risk score 122 based on the information extracted from the SCF platform 200, and further based on the financial ratios 132 received from the segregator engine 112.
  • the DCS module 114 may apply a set of predefined weights, also referred herein as weightages, to the supplier profile 104, the transaction data 108, the asset trust score 106, and the financial ratios 132, in determining the credit risk score 122.
  • the weightage assigned to the financial ratios 132 may be 40% and the weightage assigned to the SCF platform data may be 60%.
  • the weightage assigned to the financial ratios 132 may be subdivided into smaller weightages assigned to each financial ratio, for example, 10% may be assigned to the net profit margin, 10% to the return on assets, 5% to the debt to equity ratio, 5% to the debt to total asset ratio, 5% to the current ratio, and 5% to the quick ratio etc.
  • the weightages may be assigned based on the importance of individual factors in the supply chain, like risk profile of the financial institution, macro-economic trends, and platform data etc.
  • the weightages may be further modified based on availability of additional data related to other factors such as quality, social media etc.
  • the system 100 may further include a data enhancer module 116 which dynamically assigns weights or modifies the predefined weights applied by the DCS module 114.
  • the DCS module 114 may be coupled with the data enhancer module 116.
  • the data enhancer module 116 may include a weight adjustment module 134 that is configured to adjust the predefined weights based on the availability of data points in the information used by the DCS module 114 to compute the credit risk score 122.
  • the weight adjustment module 134 may calculate the weights for each input parameter to the DCS module 114, based on their respective completeness of data. Consequently, the computation of the credit risk score may depend on the availability of data or the amount of data submitted by the loan applicant during the loan application.
  • the weight adjustment module 134 may receive data related to each input parameter, for example, supplier profile 104, asset trust score 106, transaction data 108, financial ratios 132, and may determine the default quantity of data points required for each of the input parameter. The weight adjustment module 134 may programmatically check whether the user inputs match the number of default data points and identify the missing data. The weight adjustment module 134 may reduce the weightage assigned to an input parameter if there are missing data. For example, the default weightage assigned to transactions data 108 may be 20% and the required quantity of data points is 4, and when two of the data points are missing, the weight adjustment module 134 may reduce the weightage of the transactions data 108 to 10%.
  • the data enhancer module 116 may further include an artificial intelligence (Al) model 136.
  • the Al model 136 may be a machine learning model.
  • the data enhancer module 116 may train the Al model 136 based on past credit obligations met by a plurality of different loan applicants, i.e. different companies.
  • the data enhancer module 116 may determine the weightages of each input parameter to the DCS module 114, using the trained Al model 136.
  • the data enhancer module 116 may also assist the DCS module 114 in determining the credit risk score using the Al model 136.
  • the Al model 136 trained on past credit obligations data may be capable of predicting the credit risk score based on the available input data.
  • the DCS module 114 may modify the credit risk score based on the prediction from the Al model 136.
  • the credit risk score 122 presents the decision whether the loan request may be approved or rejected with recommendations.
  • the credit risk score 122 may be utilized by financial institutions to determine whether credit, i.e. loans can be offered to loan applicants. As an example, scores in the range of 7-10 may represent low risk, scores in the range 4-7 may represent moderate risk, and scores in the range of 0-4 may represent high risk.
  • the financial institutions such as banks, may reject the request for a loan if the score indicates high risk, and may offer a lower interest rate if the score indicates low risk.
  • the weightages may be further modified based on availability of additional data related to other factors such as quality, social media etc.
  • the weightages may be adjusted, for example, by the weight adjustment module 134.
  • the weightages may be preset to be equal.
  • the weightages may be determined based on the risk profile of financial institutions or economic conditions.
  • the weightages may be adjusted using fuzzy analytic hierarchic process.
  • FIG. 2 shows a conceptual hardware diagram of the system 100 according to various embodiments.
  • the system 100 may include, for example, one or more servers, workstations, personal computers, laptops, tablets, smartphones, point of service (POS) terminals, or other suitable computing devices.
  • the system 100 may include a single computing device, or it may include multiple computing devices located in close proximity, or multiple computing devices distributed over a geographic region.
  • the system 100 may include a processor 202 and a memory 204 coupled to the processor 202.
  • the processor 202 may be configured to bidirectionally communicate with the memory 204.
  • the processor 202 may include one or more processing units (e.g., in a multi-core configuration).
  • the one or more processing units may include, for example, a central processing unit (CPU), a microcontroller, a reduced instruction set computer (RISC) processor, an application specific integrated circuit (ASIC), a programmable logic device (PLD), a gate array, and/or any other circuit or processor capable of the functions described herein.
  • CPU central processing unit
  • RISC reduced instruction set computer
  • ASIC application specific integrated circuit
  • PLD programmable logic device
  • gate array any other circuit or processor capable of the functions described herein.
  • the memory 204 may permit data, instructions, etc., to be stored therein and retrieved therefrom.
  • the memory 204 may be a physical, tangible, and non-transitory computer readable storage media.
  • the memory 204 may include one or more computer-readable storage media, such as, dynamic random access memory (DRAM), static random access memory (SRAM), read only memory (ROM), erasable programmable read only memory (EPROM), solid state devices, flash drives, CD-ROMs, thumb drives, floppy disks, tapes, hard disks, and/or any other type of volatile or nonvolatile computer-readable media.
  • DRAM dynamic random access memory
  • SRAM static random access memory
  • ROM read only memory
  • EPROM erasable programmable read only memory
  • solid state devices flash drives, CD-ROMs, thumb drives, floppy disks, tapes, hard disks, and/or any other type of volatile or nonvolatile computer-readable media.
  • the memory 204 may be configured to store transaction data, other data relating to the companies or loan applicants, and/or other types of data and/or information suitable for use as described herein.
  • Computer-executable instructions may also be stored in the memory 204 for execution by the processor 202 to cause the processor 202 to perform one or more of the functions described herein.
  • the memory 204 may include a variety of different memories, each implemented in one or more of the modules of the system 100.
  • the system 100 may also include a presentation unit 206 that is coupled to the processor 202.
  • the presentation unit 206 may be in communication with the processor 202.
  • the presentation unit 206 may include an output device or display device, such as a computer monitor, or a display screen.
  • the system 100 may include output devices other than the presentation unit 206.
  • the presentation unit 206 may output information, either visually or audibly to a user of the system 100, for example, a loan applicant, or a staff of one of the financial institutions issuing the loan, or individuals associated with other parts of the system 100, etc.
  • Various interfaces may be displayed at the presentation unit 206, to display information, such as, for example, transaction data, etc.
  • the presentation unit 206 may include, for example, a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic LED (OLED) display, or an “electronic ink” display, etc. In some embodiments, the presentation unit 206 may include multiple devices.
  • LCD liquid crystal display
  • LED light-emitting diode
  • OLED organic LED
  • the presentation unit 206 may include multiple devices.
  • the system 100 may further include an input device 208.
  • the input device 208 may be configured to receive inputs from a user of the system 100.
  • the input device 208 may be coupled to, and may be configured to communication with, the processor 202.
  • the input device 208 may include, for example, a keyboard, a pointing device, a mouse, a stylus, a touch sensitive panel such as a touch pad or a touch screen, or another computing device, and/or an audio input device.
  • a touch screen such as that included in a tablet, a smartphone, or similar device, may function as both the presentation unit 206 and the input device 208.
  • the system 100 may further include a network interface 210 coupled to the processor 202.
  • the network interface 210 may also be coupled to the memory 204.
  • the network interface 210 may be communicatively coupled to the processor 202 and the memory 204.
  • the network interface 210 may include, for example, a wired network adapter, a wireless network adapter, a mobile network adapter, or other device capable of communicating to one or more different networks, including the network 110.
  • the system 100 may include the processor 202 and one or more network interfaces incorporated into or with the processor 202.
  • FIG. 3 shows a schematic diagram of a SCF platform 200 according to various embodiments.
  • the SCF platform 200 may be hosted on a blockchain network such as Hyperledger fabric.
  • ERP systems are commonly used by companies to manage their everyday business processes, and may keep track of their inventory, account receivables and other revenue-related information. As such, the ERP systems may contain private business and transactional data of companies.
  • Companies 306, 308 that join the SCF platform 200 may connect their procurement systems or enterprise resource planning (ERP) systems to the SCF platform 200, such that their supply chain data may be shared with the SCF platform 200.
  • ERP enterprise resource planning
  • the SCF platform 200 may include an import module configured to import the supply chain data from the ERP system, onto the blockchain network. The supply chain data may form part of the input data provided to the DCS module 114.
  • the SCF platform 200 may include a private ledger 310 configured to store the supply chain data of the companies, and a public ledger 312 configured to store the asset trust score 106. Each participant, i.e. participant node, of the blockchain network may hold a copy of the public ledger 312.
  • the private ledger 310 may be accessible only by the SCF platform owner.
  • the SCF platform 200 may further include a smart contract 302 configured to compute a first hash value based on the imported supply chain data.
  • the smart contract 302 may also write the imported supply chain data and the hash value to the private ledger 310.
  • the imported supply chain data may include inventory amount.
  • the hash value may be hash value of the inventory amount.
  • the private ledger 310 may store, for example, the supplier name, the inventory amount and the hash value of the inventory amount.
  • the imported supply chain data may include account receivables amount.
  • the hash value may be hash value of the account receivables amount.
  • the private ledger 310 may store, for example, the supplier name, the account receivables amount and the hash value of the account receivables amount.
  • the smart contract 302 may be further configured to calculate a first parameter.
  • the first parameter may include the asset trust score.
  • the smart contract 302 may be further configured to read the supply chain data from the private ledger 310, and further configured to compute the asset trust score 106 based on the supply chain data.
  • the smart contract 302 may also be configured to compute a second hash value based on the supply chain data, and may be configured to write the asset trust score and the hash value to the public ledger 312.
  • the smart contract 302 may compute the asset trust score 160 based on the inventory data and the account receivables, for example, based on a sum of on the inventory data and the account receivables.
  • the asset trust score 160 may be indicative of the company’s ability to service its loan, i.e. to pay back the loan either by instalments or by lump sum repayment. As such, the asset trust score may serve as a digital collateral.
  • the smart contract 302 may also compute the second hash value based on a combination of the inventory data and the account receivables.
  • the smart contract 302 may re-compute the first parameter and may generate an updated second hash value based on the changed input data. For example, whenever there are changes in the supply chain data, the smart contract 302 may re-compute the asset trust score 106 and may generate an updated second hash value based on the changed supply chain data. The smart contract 302 may also write the updated second hash value and the updated asset trust score 106 to the public ledge 312. The smart contract 302 may also be activated when a request for loan is submitted to the SCF platform 200. As the asset trust score 106 is stored by each node of the blockchain network, the loan applicant, or any other participant of the SCF platform 200 would not be able to manipulate the asset trust score.
  • the SCF platform 200 may include a first smart contract and a second smart contract instead of a single smart contract 302.
  • the first smart contract may be connected to the private ledger 310 while the second smart contract may be connected to tthe public ledger 312.
  • the first smart contract may be configured to compute the first hash value based on the imported supply chain data, and may also write the imported supply chain data and the hash value to the private ledger 310.
  • the second smart contract may be configured to read the supply chain data from the private ledger 310, and further configured to compute the asset trust score 106 based on the supply chain data.
  • the second smart contract may also be configured to compute a second hash value based on the supply chain data, and may be configured to write the asset trust score and the hash value to the public ledger 312.
  • the second smart contract may compute the asset trust score 160 based on the inventory data and the account receivables, and may re-compute the asset trust score 106 and may generate an updated second hash value when there are changes to the supply chain data.
  • the second smart contract 302 may also write the updated second hash value and the updated asset trust score 106 to the public ledger 312.
  • FIG. 4A shows a flowchart 400A of a method of assessing credit risk according to various embodiments.
  • the method may include determining a plurality of parameters based on input data, in 402.
  • the input data may include audited statements 102, supplier profile 104, supply chain data, and transaction data 108.
  • the audited statements 102 may include financial statements.
  • the plurality of parameters may include the financial ratios 132, the asset trust score and other parameters relating to the supplier profile 104 and the transaction data 108.
  • the plurality of parameters may include a first parameter.
  • the first parameter may include the asset trust score.
  • the method may include adjusting weights based on data completeness, in 404.
  • Adjusting the weights based on completeness may include adjusting a predefined weightage for each parameter of the plurality of parameters, based on a quantity of data points in the input data that relates to the respective parameter.
  • the process of adjusting the weights may be carried out by the data enhancer 116.
  • the method may include computing the credit risk score 122, in 406.
  • the process of computing the credit risk score 122 may be carried out by the DCS module 114.
  • FIG. 4B shows a flowchart 400B of a method of assessing credit risk according to various embodiments.
  • the flowchart 400A may include the processes 404 and 406.
  • the method may further include obtaining supply chain data, in 408.
  • the supply chain data may form part of the input data.
  • the supply chain data may be obtained from the SCF platform 200.
  • the supply chain data may include company profile and transactions data.
  • the supply chain data may include inventory amount and account receivables.
  • the first parameter may be calculated based on the supply chain data. For example, the asset trust score may be determined based on the inventory amount and account receivables.
  • the method may further include obtaining financial data, in 410.
  • the financial data may include the financial ratios 132.
  • Obtaining the financial data may include computing the financial ratios 132 based on information extracted from audited financial statements such as balance sheet, cash flow and income statements.
  • the financial data referred to in 410 and the supply chain data referred to in 408 may be part of the input data referred to in 402.
  • the method may further include calculating the asset trust score 106, in 412.
  • the asset trust score 106 may be calculated by the SCF platform 200, based on supply chain data such as inventory amount and account receivables.
  • the asset trust score 106 may be one of the parameters referred to in 402.
  • FIG. 5 shows a formula 500 that represents the weightage determination logic of the weight adjustment module 134, according to various embodiments.
  • the formula 500 indicates: [0048] W(supplier pro file, asset trust score, transactions, financials) ma Y represent the adjusted weightages for each input parameter, such as supplier profile 104, asset trust score 106, transaction data 108 and financial ratios 132.
  • W de ⁇ auU may represent the default weightages which are predefined by either the user, or by the data enhancer 116 based on the Al model 136.
  • the weight adjustment module 134 may assess the completeness of the input data relating to the input parameters, and may compute the adjusted weightages, based on the completeness of the input data.
  • Count parameters may represent the default quantity of data points required for the respective input parameter.
  • Count missin g may represent the quantity of missing data points. According to the formula 500, the adjust weightage would be low when Count missin gis high. In other words, the significance of an input parameter for determining the credit risk score may be reduced if its associated data is incomplete.
  • FIG. 6 shows a table 600 that lists examples of the inputs and outputs of the segregator engine 112, according to various embodiments.
  • First column 602 of the table 600 lists the key factors to consider for assessment.
  • Second column 604 lists the financial ratios 132 relating to the key factors.
  • Third column 606 lists the line items in the financial statements or audited statements 102 that relate to the key factors.
  • the segregator 112 may extract information from the line items listed in the third column 606, to compute the financial ratios 132 listed in the second column 604.
  • the key factors to consider for assessment may include liquidity and cash flow, profitability, and solvency ratio and stable financial debt.
  • the financial ratios 132 that are indicative of liquidity and cash flow may include current ratio and quick ratio.
  • the segregator engine 112 may compute the current ratio based on dividing the difference between current assets and inventories over the current liabilities.
  • the segregator engine 112 may compute the quick ratio based on dividing the net profit over the total revenue.
  • the financial ratios 132 that are indicative of profitability may include net profit margin and return on assets.
  • the segregator engine 112 may compute the net profit margin and the return on assets based on net income and total assets.
  • the financial ratios 132 that are indicative of solvency ratio and stable financial debt may include debt to equity ratio and debt to total asset ratio.
  • the segregator engine 112 may compute the debt to equity ratio based on dividing total liabilities over the total shareholders equity.
  • the segregator engine 112 may compute the debt to total asset ratio based on dividing the total liabilities over the total assets.
  • FIG. 7 shows examples of the types of data in the audited statements 102, which are input to the segregator engine 112, according to various embodiments.
  • First table 702 shows the types of information extracted from the balance sheets.
  • Second table 704 shows the types of information extracted from cash flow statements.
  • Third table 706 shows the types of information extracted from income statements. The data contents of these tables 702, 704 and 706 may be used by the segregator engine 112 to compute financial ratios 132.
  • Combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of A, B, and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof’ include any combination of A, B, and/or C, and may include multiples of A, multiples of B, or multiples of C.
  • combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of A, B, and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof’ may be A only, B only, C only, A and B, A and C, B and C, or A and B and C, where any such combinations may contain one or more member or members of A, B, or C.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Computer Security & Cryptography (AREA)
  • Economics (AREA)
  • Technology Law (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Health & Medical Sciences (AREA)
  • Bioethics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

Procédé d'évaluation de risque de crédit d'une société. Le procédé peut consister à déterminer une pluralité de paramètres sur la base de données d'entrée concernant la société. Le procédé peut en outre consister à régler une pondération prédéfinie pour chaque paramètre de la pluralité de paramètres sur la base d'une quantité de points de données dans les données d'entrée qui concernent le paramètre respectif. Le procédé peut également consister à calculer un indice de risque de crédit sur la base de la pluralité de paramètres et de leurs pondérations réglées respectives. L'invention concerne également une plateforme de financement de chaîne d'approvisionnement hébergée sur un réseau de chaîne de blocs. La plateforme de financement de chaîne d'approvisionnement peut comprendre un grand livre privé configuré pour stocker des données de chaîne d'approvisionnement d'une société. La plateforme de financement de chaîne d'approvisionnement peut en outre comprendre un grand livre privé configuré pour stocker des données de chaîne d'approvisionnement d'une société. La plateforme de financement de chaîne d'approvisionnement peut en outre comprendre un contrat intelligent configuré pour lire les données de chaîne d'approvisionnement depuis le grand livre privé et configuré en outre pour calculer un premier paramètre sur la base des données de chaîne d'approvisionnement, ainsi qu'une valeur de hachage sur la base des données de chaîne d'approvisionnement. La plateforme de financement de chaîne d'approvisionnement peut en outre comprendre un grand livre public, le contrat intelligent étant en outre configuré pour écrire le premier paramètre et la valeur de hachage dans le grand livre public.
PCT/SG2021/050525 2021-08-31 2021-08-31 Procédé d'évaluation de risque de crédit d'une société et plateforme de financement de chaîne d'approvisionnement hébergée sur un réseau de chaîne de blocs WO2023033708A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/SG2021/050525 WO2023033708A1 (fr) 2021-08-31 2021-08-31 Procédé d'évaluation de risque de crédit d'une société et plateforme de financement de chaîne d'approvisionnement hébergée sur un réseau de chaîne de blocs

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/SG2021/050525 WO2023033708A1 (fr) 2021-08-31 2021-08-31 Procédé d'évaluation de risque de crédit d'une société et plateforme de financement de chaîne d'approvisionnement hébergée sur un réseau de chaîne de blocs

Publications (1)

Publication Number Publication Date
WO2023033708A1 true WO2023033708A1 (fr) 2023-03-09

Family

ID=85412651

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/SG2021/050525 WO2023033708A1 (fr) 2021-08-31 2021-08-31 Procédé d'évaluation de risque de crédit d'une société et plateforme de financement de chaîne d'approvisionnement hébergée sur un réseau de chaîne de blocs

Country Status (1)

Country Link
WO (1) WO2023033708A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117237123A (zh) * 2023-11-15 2023-12-15 山东政信大数据科技有限责任公司 基于区块链的金融信用风险智能管控方法及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170140461A1 (en) * 2014-03-05 2017-05-18 Marc Abramowitz System and method for generating a dynamic credit risk rating for a debt security
US20190026667A1 (en) * 2016-03-24 2019-01-24 Www.Trustscience.Com Inc. Learning an entity's trust model and risk tolerance to calculate its risk-taking score
US20200234218A1 (en) * 2019-01-18 2020-07-23 Samuel Salloum Systems and methods for entity performance and risk scoring
CN112446794A (zh) * 2020-10-14 2021-03-05 天津航空物流发展有限公司 基于区块链的供应链金融信用评价系统及方法
US20210166167A1 (en) * 2019-12-02 2021-06-03 Asia University Artificial intelligence and blockchain-based inter-enterprise credit rating and risk assessment method and system
US20210203482A1 (en) * 2018-12-07 2021-07-01 Tencent Technology (Shenzhen) Company Limited Method for recording data block in blockchain network, accounting node, and medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170140461A1 (en) * 2014-03-05 2017-05-18 Marc Abramowitz System and method for generating a dynamic credit risk rating for a debt security
US20190026667A1 (en) * 2016-03-24 2019-01-24 Www.Trustscience.Com Inc. Learning an entity's trust model and risk tolerance to calculate its risk-taking score
US20210203482A1 (en) * 2018-12-07 2021-07-01 Tencent Technology (Shenzhen) Company Limited Method for recording data block in blockchain network, accounting node, and medium
US20200234218A1 (en) * 2019-01-18 2020-07-23 Samuel Salloum Systems and methods for entity performance and risk scoring
US20210166167A1 (en) * 2019-12-02 2021-06-03 Asia University Artificial intelligence and blockchain-based inter-enterprise credit rating and risk assessment method and system
CN112446794A (zh) * 2020-10-14 2021-03-05 天津航空物流发展有限公司 基于区块链的供应链金融信用评价系统及方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LI JIAN, ZHU SHICHAO, ZHANG WEN, YU LEAN: "Blockchain-driven supply chain finance solution for small and medium enterprises", FRONTIERS OF ENGINEERING MANAGEMENT, vol. 7, no. 4, 1 December 2020 (2020-12-01), pages 500 - 511, XP009544174, ISSN: 2095-7513, DOI: 10.1007/s42524-020-0124-2 *
MA CHAOQUN, KONG XIAOLIN, LAN QIUJUN, ZHOU ZHONGDING: "The privacy protection mechanism of Hyperledger Fabric and its application in supply chain finance", CYBERSECURITY, vol. 2, no. 1, 1 December 2019 (2019-12-01), XP055823876, DOI: 10.1186/s42400-019-0022-2 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117237123A (zh) * 2023-11-15 2023-12-15 山东政信大数据科技有限责任公司 基于区块链的金融信用风险智能管控方法及系统
CN117237123B (zh) * 2023-11-15 2024-03-01 山东政信大数据科技有限责任公司 基于区块链的金融信用风险智能管控方法及系统

Similar Documents

Publication Publication Date Title
US20240119463A1 (en) System and method for managing transactions in dynamic digital documents
Barth et al. How did financial reporting contribute to the financial crisis?
Gourieroux et al. Bilateral exposures and systemic solvency risk
Milevsky et al. A sustainable spending rate without simulation
US9213993B2 (en) Investment, trading and accounting management system
Ahmed Risk management assessment systems: an application to Islamic banks
Barbosa et al. Determinants of the real exchange rate in the long-run for developing and emerging countries: a theoretical and empirical approach
US20140279404A1 (en) Systems and methods for assumable note valuation and investment management
Van den End Liquidity stress-tester: do Basel III and unconventional monetary policy work?
Pennanen Arbitrage and deflators in illiquid markets
Mo et al. Financial distress and commodity hedging: Evidence from Canadian oil firms
US10671952B1 (en) Transmission of a message based on the occurrence of a workflow event and the output of an externally augmented propensity model identifying a future financial requirement
Glass et al. Modelling the performance of Irish credit unions, 2002 to 2010
Feijo et al. Investment cycle of the Brazilian economy: a panel cointegration analysis of industrial firms based on Minsky’s financial instability hypothesis—2007–2017
JP3967927B2 (ja) 信用格付けシステム
Manguzvane et al. GAS Copula models on who’s systemically important in South Africa: Banks or Insurers?
Moosa Quantification of operational risk under Basel II: the good, bad and ugly
WO2023033708A1 (fr) Procédé d'évaluation de risque de crédit d'une société et plateforme de financement de chaîne d'approvisionnement hébergée sur un réseau de chaîne de blocs
Scorte et al. The importance of accounting information in crisis times
Demianchuk et al. The influence of globalization and integration processes on the activity of insurance organizations
Loader Advanced operations management
Babajide et al. Assessment of financial stability in emerging economies: Evidence from Nigeria
Golding et al. Analysis of the Proposed 2020 FHFA Rule on Enterprise Capital
Wei et al. Bank risk aggregation based on the triple perspectives of bank managers, credit raters, and financial analysts
TWM597935U (zh) 特約商店風險評估系統

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21956202

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21956202

Country of ref document: EP

Kind code of ref document: A1