WO2021075949A1 - Traitement de données pour la gestion de limites dans des institutions financières - Google Patents

Traitement de données pour la gestion de limites dans des institutions financières Download PDF

Info

Publication number
WO2021075949A1
WO2021075949A1 PCT/MY2020/050104 MY2020050104W WO2021075949A1 WO 2021075949 A1 WO2021075949 A1 WO 2021075949A1 MY 2020050104 W MY2020050104 W MY 2020050104W WO 2021075949 A1 WO2021075949 A1 WO 2021075949A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
entity
processing
attributes
facility
Prior art date
Application number
PCT/MY2020/050104
Other languages
English (en)
Inventor
Meenakshy R IYER
Santosh K DESHPANDE
Prathish VARGHESE
Mohd Suhail Amar Suresh ABDULLAH
Original Assignee
Malayan Banking Berhad
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 Malayan Banking Berhad filed Critical Malayan Banking Berhad
Publication of WO2021075949A1 publication Critical patent/WO2021075949A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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

Definitions

  • the present invention relates to data processing in financial institutions. More particularly, the invention relates to system and method for AI (artificial intelligence) based data processing for limits management in banks or other financial institutions.
  • AI artificial intelligence
  • the risk criteria differs across customers as numerous operational and business environments are associated with diverse level of risk.
  • the existing systems for risk assessment due to stiff approach and coupled with manual interventions, do not accurately handle the dynamism of changes that occur in operation and business.
  • the changes in real time environments and their impact on multiple functions are important criteria to determine the risk involved.
  • every bank sets the policy limits based on such risk factors and appropriate determination of such risks to assess a required transaction is essential for enabling the bank to function properly.
  • the risk assessment based on policy limits may be a time-consuming exercise which may impact the customer service and thereby lead to loss of customer for the bank.
  • Any banking institute invests lot of time and money in marketing to try and increase the customer base but at the same time, banks need to ensure the risk assessment for every customer is appropriate to avoid losses later. The banks always strive to strike a balance in determining the risks and that too in least possible time to ensure success.
  • Manual determination of affected limits for Policy Limits or No Single Constituent Limits is time consuming, non-integrated, prone to factual errors and miss-out parameters or dimensions, lag time in recording and data retrieve in the absence of a common, coherent platform.
  • the present invention provides a data processing method for limit management in a financial institution.
  • the method includes the steps of receiving by a processor at least one entity data attributes; receiving a selection of a facility data attributes based on requirement of at least one entity; analyzing a set of data models stored in a data model database to identify at least one model for processing the received entity data attributes and facility data attributes; processing the received entity data attributes, facility data attributes and a set of associated parameters of the facility data based on the at least one identified data model for determining the requirement of the at least one entity; and AI based processing of a data matrix and the identified data model to determine by a controller at least one limit set for processing the requirement wherein the data matrix includes entity data attributes and facility data attributes.
  • the present invention provides a system for limit management in financial institution.
  • the system includes an electronic user interface configured for operating on a limit management application, at least one entity database configured for storing a plurality of entity data attributes and a set of associated parameters of the entity data, at least one facility database configured for storing a plurality of facility data attributes and a set of associated parameters of the facility data and a controller encoded with instructions enabling the controller to function as a hot wherein the controller is configured to perform functions of analyzing a set of data models stored in a data model database to identify at least one model for processing the received entity data attributes and facility data attributes; processing the received entity data attributes, facility data attributes and a set of associated parameters of the facility data based on the at least one identified data model for determining the requirement of the at least one entity.
  • the system includes a processor coupled to the controller for AI based processing of a data matrix and the identified data model to determine at least one limit set for processing the requirement wherein the data matrix includes entity data attributes and facility data attributes.
  • the present invention provides a computer-readable non-transitory storage medium storing executable program instructions for data processing for limits management in financial institution by a configurable application which when executed by a computer causes the computer to perform operations as described above.
  • Fig. 1 shows a system architecture of data processing for limits management in accordance with an embodiment of the present invention.
  • Fig. 2 shows a structural layer architecture of the data processing for limits management in financial institutions in accordance with an embodiment of the present invention.
  • Fig. 3 shows a flowchart depicting a data processing method for limit management in financial institution in accordance with an embodiment of the present invention.
  • Embodiments described herein refer to plan views and/or cross-sectional views by way of ideal schematic views. Accordingly, the views may be modified depending on simplistic assembling or manufacturing technologies and/or tolerances. Therefore, example embodiments are not limited to those shown in the views but include modifications in configurations formed on basis of assembling process. Therefore, regions or regions of elements exemplified in the figures have schematic properties and shapes, and do not limit the various embodiments including the example embodiments.
  • the system 100 include at least one computing device 110, a server support architecture 120, a data processing and control support architecture/mechanism 130, and a policy limit database 140a.
  • the server support architecture may include server 120a and mainframe 120b.
  • the data processing and control support architecture/mechanism 130 may include a processor 130a and a controller 130b.
  • the system may include a data model database 140b.
  • the application has the list of parameters, its reference values, data attributes related to customer data and facility data, policy data as underlying seeded data in the policy limit database (140a). This is used by the logic of limit management for processing - by mapping the received input values against these seeded policy data. Any addition or change in parameters/reference values/ in database is made by an interface.
  • the at least one entity database is configured for storing a plurality of entity data and a set of associated parameters of the entity data including facility data.
  • a seed data model of the application reconfigures an underlining seeded mapping structure of the application in response to determination of a received data as a new or modified policy data.
  • the controller is encoded with instructions enabling the controller to function as a hot where the controller is configured to perform functions of analyzing a set of data models stored in the data model database to identify at least one affected limits parameter from the received entity data and seeded policy data for processing the received data and AI based processing of a data matrix to determine by the controller at least one affected limit data, factor, component, sequence and protocol of the application.
  • the affected limit data are customer parameters received as an input and used to arrive at risk determination.
  • the components are various parts of limits management application wherein the risk is a composite entity.
  • the application has model identification component, policy limits component and affected attribute component.
  • the sequence is the order in which these components interact with each other to arrive at limits management requirement.
  • the protocols or rules are instructions to be followed during presence or absence of certain factors/combination of factors.
  • the modified factors/ rules for model identification and affected limits are updated and configured using the user interface to these components which then follow a sequence to arrive at risks.
  • These components consume the inputs so updated or configured without code change, as methods with relevant integrations and configurable dependencies, are embedded within in the application. Hence, the modified or new inputs which are thus configured are auto identified by the components for data processing for limits management.
  • an exposure may be broadly classified into Customer and Facility attributes. This combination may vary from one exposure to the other.
  • Front- end facility originators would specify for every facility a list of such attributes, in other words, Affected Dimensions.
  • the affected dimensions may be: a. Country of customer incorporation: Malaysia; b. Customer industry: Iron and Steel Manufacturing; c. Country of facility exposure: Malaysia; d. Facility Tenor: 10 year; Amortization type: Balloon payment, etc.
  • the data processing system and method of the present invention accepts these attributes and compares them with attributes on which bank has set limits on.
  • the Policy limits may be composed of several levels in a hierarchy (or definition). Assuming there are three Affected Dimensions, an Affected Limits algorithm parses through all combinations to determine list of policy limit definitions which need to be checked/updated for availability of limits, without any manual intervention. The result of each Affected Limit check would be to state broadly, if limits are available per each Affected Limit to grant new facilities (and update) or not, in record time. To perform the same manual check per facility request at several times a day is time inefficient and prone to errors. The Affected Limits Determination algorithm is executed within the limits management application, with the result sent back to the front-end origination system requesting this dynamic, automated check. Such origination systems may need to provide for capability to send attributes and display results through the API built in limits management application.
  • the processor is coupled to the controller for reconfiguring the set of associated parameters, the set of data models and the data matrix for determination of affected limit of the at least one entity based on the pre-set policy limits of the financial institutions.
  • the system 100 includes an electronic user interface configured for operating the system to determine affected limits.
  • the server 120a may include electronic circuitry for enabling execution of various steps by the processor.
  • the electronic circuity may have various elements including but not limited to a plurality of arithmetic logic units (ALU) and floating- point Units (FPU), and/or the equivalents thereof.
  • ALU arithmetic logic units
  • FPU floating- point Unit
  • the ALU enables processing of binary integers to assist in generating a plurality of data models to be stored in the data model database 140 to identify at least one data model for processing the received entity data and AI based processing of the data matrix and the identified data model to determine affected limits.
  • the server electronic circuitry includes at least one arithmetic logic unit, floating point units (FPU), other processors, memory, storage devices, high-speed interfaces connected through buses for connecting to memory and high-speed expansion ports, and a low speed interface connecting to low speed bus and storage device.
  • FPU floating point units
  • Each of the components of the electronic circuitry are interconnected using various busses, and may be mounted on a common motherboard or in other manners as appropriate.
  • the processor can process instructions for execution within the server 120a, including instructions stored in the memory or on the storage devices to display graphical information for a GUI on an external input/output device, such as display coupled to high speed interface.
  • multiple processors and/or multiple busses may be used, as appropriate, along with multiple memories and types of memory.
  • multiple servers may be connected, with each server providing portions of the necessary operations (e.g., as a server bank, a group of blade servers, or a multi-processor system).
  • the Processor 130a may communicate with a user through a control interface and display interface coupled to a display.
  • the display may be, for example, a TFT LCD (Thin-Film- Transistor Liquid Crystal Display) or an OLED (Organic Light Emitting Diode) display, or other appropriate display technology.
  • the display interface may comprise appropriate circuitry for driving the display to present graphical and other information to an entity/user.
  • the control interface may receive commands from a user and convert them for submission to the processor.
  • an external interface may be provided in communication with processor 130a, so as to enable near area communication of device with other devices. External interface may be suitable, for example, for wired communication in some implementations, or for wireless communication in other implementations, and multiple interfaces may also be used.
  • the database 140a is part of a data storage support architecture 140 that may include memory units that may be a volatile, a non-volatile memory or memory may also be another form of computer-readable medium, such as a floppy disk device, a hard disk device, an optical disk device, a tape device, a flash memory or other similar solid state memory device, or an array of devices, including devices in a storage area network or other configurations.
  • memory units may be a volatile, a non-volatile memory or memory may also be another form of computer-readable medium, such as a floppy disk device, a hard disk device, an optical disk device, a tape device, a flash memory or other similar solid state memory device, or an array of devices, including devices in a storage area network or other configurations.
  • the artificial intelligence-based AI engine is configured for processing a plurality of data models associated with the entity data and policy data for determining the affected limits.
  • the system of the present invention includes a natural language processing (NLP) server configured for processing the protocols based on the identified data models to determine the affected limits.
  • NLP natural language processing
  • the user interface and an underlying logic of the affected limits application is based on the seeded mapping wherein on introduction of the new or modified policy data the system automatically reconfigures the underlining seeded mapping structure of the application to include the impacted limits factors, the components, the sequence and the protocol for determination of the affected limits for an entity.
  • the application functions on seeded data and generates mapping structures or codes on basis of the seeded data thereby enabling real time processing of received entity data within the application upon receipt of new or modified data.
  • a limit management algorithm would ascertain the affected dimensions, to then look for limits based on such dimension(s) in a global data repository of limits. Information is readily retrievable and is expected to determine limits position quickly. Algorithm traverses through each of the affected limits to ascertain which limits have to be considered for subsequent actions. Affected Limits are determined based on unique customer and facility attributes. These may vary from regions or systems which originate facilities. Some attributes may change, or new ones may come in over the life of customer's association/facilities with the bank. Since the affected Limit Determination algorithm uses customer and facility attributes, the system parses through a number of predefined limits looking to determine if the list of attributes passed to it are present in each of such limit definitions. Output of this service would be used in subsequent limit management steps.
  • the affected Limits Determination algorithm would be highly configurable, callable on demand, scalable, not coded to each source system, country, market or measure. Code would not have to change when attributes are added or changed.
  • the algorithm may be used to prompt additional limit definitions which may also have to be included as part of the determination. This algorithm expedites the retrieve and update capability across all Policy or No Single Constituent Limits.
  • a structural layer diagram 200 depicting a limit determination system is provided in accordance with an embodiment of the present invention.
  • the system layer includes web layer 210, service layer 220 and repository layer 230.
  • protocols/rules can be defined by user interface for the rule engine component to consume.
  • the intermediate rules, if any, during computation of affected limits are executed within the logic of limits calculation.
  • customer level rules are executed by rule engine component.
  • a flowchart 300 depicting a data processing method for limit management in financial institution includes the step of (S310) receiving by a processor at least one entity data attributes; (S320) receiving a selection of a facility data attributes based on requirement of at least one entity; (S330) analyzing a set of data models stored in a data model database to identify at least one model for processing the received entity data attributes and facility data attributes; (S340) processing the received entity data attributes, facility data attributes and a set of associated parameters of the facility data based on the at least one identified data model for determining the requirement of the at least one entity; and (S350) AI based processing of a data matrix and the identified data model to determine by a controller at least one limit set for processing the requirement wherein the data matrix includes entity data attributes and facility data attributes.
  • a new or modified policy data impacts the assessment based on entity data or new associated parameter of the data.
  • the received data and associated parameters are compared with a set of stored policy limits data to determine if the received data to determine risks and decide approval or rejections.
  • the received data is identified, sorted, classified and analyzed as part of comparison with the set of stored Policy data.
  • the method of the present invention includes generating the data matrix that enables identification of the affected data, the components, the sequence and triggers the protocols to process the received data for determining the affected limits.
  • the method of the invention includes storing a set of rules or protocols in a memory to be executed by an AI engine coupled to a processor for generating a plurality of data models associated with the entity data to identify the at least one model for limit management.
  • the machine learning data model is configured to map entity data and data models with data processing protocol to compute affected limits. For example, output generated over the model may provide an indication of whether a particular object or class of objects is present, and optionally user instructions.
  • the machine learning model is configured to map new or modified Policy data for determining limits. Accordingly, in those implementations a single pass over a single machine learning model may be utilized to detect whether each of multiple objects is present.
  • the customer parameters with facility values are the data fed to the application, which then utilizes this input data to arrive at an appropriate data model to assess affected limit management.
  • the processor further filters these input data according to the data dependencies of the identified model and arrives at the results for the factors based on the seeded mapping in data base.
  • the method for limit management for the entity is as per the mathematical expressions linked to the model, factors and groups of factors, which can involve data received in multiple layers. The methods are designed to handle input data received in various granularity as well.
  • Multi-level rule engine integration utilizes the required input data to handle specific scenarios. Model level configuration of seeded data for values in case of exceptional scenarios is provided along with relevant dependencies.
  • the system and method computes affected limits for a customer based on definable factors. It considers multiple parameters and their interdependencies for computation. Various protocols are imbibed in the process to arrive at the affected limits. Thus, multiple parameters of varied customers are factored-in, thereby catering to diverse requests to arrive at affected limits. This allows the bank to determine the level of risk they expose themselves to by arriving at affected limits with no manual intervention. The parameters, rules and dependencies considered for this computation are fully definable. Any future change of these underlying factors and rules used for computation can be absorbed by this service without code change.
  • the invention provides flexibility and ease of use of the application coupled with a design which reflects risk in its entirety.
  • the system and method of the present invention is robust to absorb multiple real time changes and function without interruptions in case of update of factors as well as their interdependencies.
  • the real time changes are due to modification in external factors or regulatory requirements.
  • the interdependencies of the entity parameters considered for determination of affected limits are also subject to change, leading to an expected variation in the limits.
  • the invention provides a configurable application, which allows configuration of multiple models of affected limits.
  • the variation of interdependencies and its effect on the limits is handled by protocols.
  • New models and the protocols are configured at any juncture, thereby allowing addition or update of entity customer parameters and its interdependencies dynamically.
  • certain portions of the invention may be implemented as a “component” or “system” that performs one or more functions.
  • These components/systems may include hardware, such as a processor, an ASIC (Application Specific Integrated Circuit), or a FPGA (Field Programmable Gate Array), or a combination of hardware and software.
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • exemplary is used herein to mean “serving as an example.” Any embodiment or implementation described as “exemplary'” is not necessarily to be construed as preferred or advantageous over other embodiments or implementations.
  • Each of the above identified processes corresponds to a set of instructions for performing a function described above.
  • the above identified programs or sets of instructions need not be implemented as separate software programs, procedures or modules, and thus various subsets of these modules may be combined or otherwise re-arranged in various embodiments. For example, embodiments may be constructed in which steps are performed in an order different than illustrated, steps are combined, or steps are performed simultaneously, even though shown as sequential steps in illustrative embodiments.
  • the terminology used herein is for the purpose of description and should not be regarded as limiting.
  • the use of “including,” “comprising,” “having,” “containing” and variations thereof herein, is meant to encompass the items listed thereafter and equivalents thereof as well as additional items.
  • the embodiments may be implemented in any of numerous ways.
  • the embodiments may be implemented using various combinations of hardware and software and communication protocol(s). Any standard communication or network protocol may be used and more than one protocol may be utilized.
  • the software code may be executed on any suitable processor or collection of processors, whether provided in a single computer or distributed among multiple computers.
  • processors may be implemented as integrated circuits, with one or more processors in an integrated circuit component, or any other suitable circuitry.
  • a computer may be embodied in any of a number of forms, such as a rack-mounted computer, a desktop computer, a laptop computer, single board computer, micro-computer, or a tablet computer.
  • a computer may be embedded in a device not generally regarded as a computer but with suitable processing capabilities, including a Personal Digital Assistant (PDA), a smart phone or any other suitable portable or fixed electronic device.
  • PDA Personal Digital Assistant
  • the various methods or processes outlined herein may be coded as software that is executable on one or more processors that employ any one of a variety of operating systems or platforms. Additionally, such software may be written using any of a number of suitable programming languages and/or programming or scripting tools or a combination of programming languages, and also may be compiled as executable machine language code or intermediate code that is executed on a framework or a virtual machine.
  • the invention may be embodied as a computer readable storage medium (or multiple computer readable media) (e.g., a computer memory, one or more floppy discs, compact discs (CD), optical discs, digital video disks (DVD), magnetic tapes, flash memories, circuit configurations in Field Programmable Gate Arrays or other semiconductor devices, or other tangible computer storage medium) encoded with one or more programs that, when executed on one or more computers or other processors, perform methods that implement the various embodiments of the invention discussed above.
  • a computer readable storage medium may retain information for a sufficient time to provide computer-executable instructions in a non-transitory form.
  • program or “software” are used herein in a generic sense to refer to any type of computer code or set of computer-executable instructions that may be employed to program a computer or other processor to implement various aspects of the present invention as discussed above. Additionally, it should be appreciated that according to one aspect of this embodiment, one or more computer programs that when executed perform methods of the present invention need not reside on a single computer or processor but may be distributed in a modular fashion amongst a number of different computers or processors to implement various aspects of the present invention.
  • Computer-executable instructions may be in many forms, such as program modules, executed by one or more computers or other devices. Also, data structures may be stored in computer-read able media in any suitable form.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Technology Law (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

La présente invention concerne un système et un procédé de traitement de données pour la gestion de limites. Le système selon l'invention est un système configurable pour calculer des exigences d'une entité sur la base d'attributs de données d'entité, d'attributs de données d'installation et de paramètres associés. Le système comporte au moins un dispositif informatique, une architecture de support de serveur, une architecture de support de commande et de traitement de données, et une base de données de limites de politique. Le mécanisme de support de commande et de traitement de données peut comporter un processeur et un dispositif de commande, le processeur étant couplé au dispositif de commande pour un traitement, basé sur l'IA, d'une matrice de données et du modèle de données identifié pour déterminer au moins un ensemble de limites pour traiter l'exigence, la matrice de données comportant des attributs de données d'entité et des attributs de données d'installation.
PCT/MY2020/050104 2019-10-14 2020-10-14 Traitement de données pour la gestion de limites dans des institutions financières WO2021075949A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
MYPI2019006061 2019-10-14
MYPI2019006061 2019-10-14

Publications (1)

Publication Number Publication Date
WO2021075949A1 true WO2021075949A1 (fr) 2021-04-22

Family

ID=75537958

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/MY2020/050104 WO2021075949A1 (fr) 2019-10-14 2020-10-14 Traitement de données pour la gestion de limites dans des institutions financières

Country Status (1)

Country Link
WO (1) WO2021075949A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160048766A1 (en) * 2014-08-13 2016-02-18 Vitae Analytics, Inc. Method and system for generating and aggregating models based on disparate data from insurance, financial services, and public industries
US20180182029A1 (en) * 2016-12-22 2018-06-28 American Express Travel Related Services Company, Inc. Systems and methods for custom ranking objectives for machine learning models applicable to fraud and credit risk assessments
US20190043127A1 (en) * 2017-08-04 2019-02-07 Airbnb, Inc. Verification model using neural networks
US20190102835A1 (en) * 2017-10-03 2019-04-04 Cerebro Capital, Inc. Artificial intelligence derived anonymous marketplace
US20190205977A1 (en) * 2018-01-03 2019-07-04 QCash Financial, LLC Statistical risk management system for lending decisions

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160048766A1 (en) * 2014-08-13 2016-02-18 Vitae Analytics, Inc. Method and system for generating and aggregating models based on disparate data from insurance, financial services, and public industries
US20180182029A1 (en) * 2016-12-22 2018-06-28 American Express Travel Related Services Company, Inc. Systems and methods for custom ranking objectives for machine learning models applicable to fraud and credit risk assessments
US20190043127A1 (en) * 2017-08-04 2019-02-07 Airbnb, Inc. Verification model using neural networks
US20190102835A1 (en) * 2017-10-03 2019-04-04 Cerebro Capital, Inc. Artificial intelligence derived anonymous marketplace
US20190205977A1 (en) * 2018-01-03 2019-07-04 QCash Financial, LLC Statistical risk management system for lending decisions

Similar Documents

Publication Publication Date Title
US11501304B2 (en) Systems and methods for classifying imbalanced data
US10346782B2 (en) Adaptive augmented decision engine
CN111967779A (zh) 一种风险评估方法、装置及设备
US20140019295A1 (en) Automated Technique For Generating Recommendations Of Potential Supplier Candidates
TWI830722B (zh) 用於事件機器執行模型的系統及方法
US9392012B2 (en) Application security testing system
US10733175B2 (en) Data warehouse model validation
US11829455B2 (en) AI governance using tamper proof model metrics
US11803792B2 (en) Risk management
CN113094414A (zh) 流转图谱生成方法及装置
US9904922B2 (en) Efficient tail calculation to exploit data correlation
US20200327615A1 (en) Portfolio risk measures aggregation
US20230186070A1 (en) Artificial intelligence based data processing in enterprise application
US20230116345A1 (en) Systems and methods for enterprise wide risk assessment and aggregated risk analysis
WO2021075949A1 (fr) Traitement de données pour la gestion de limites dans des institutions financières
Khan et al. Users sentiment analysis using artificial intelligence-based FinTech data fusion in financial organizations
US20150294328A1 (en) Customer Relationship Prediction and Valuation
WO2021075952A1 (fr) Produit d'intérêts estimé
WO2021075954A1 (fr) Diligence raisonnable pour l'atténuation de risque
WO2021075953A1 (fr) Test de résistance
US20230117012A1 (en) Method and system for generating approval predictions for financial service requests
US20230060245A1 (en) System and method for automated account profile scoring on customer relationship management platforms
US12045825B2 (en) Linguistic transformation based relationship discovery for transaction validation
CN111625556B (zh) 一种基于征信的订单匹配方法、装置、设备及存储介质
US20220351210A1 (en) Method and system for detection of abnormal transactional behavior

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: 20876411

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 07-09-2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20876411

Country of ref document: EP

Kind code of ref document: A1