CN111415247B - Post-credit risk evaluation method and device, storage medium and electronic equipment - Google Patents
Post-credit risk evaluation method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN111415247B CN111415247B CN202010335871.4A CN202010335871A CN111415247B CN 111415247 B CN111415247 B CN 111415247B CN 202010335871 A CN202010335871 A CN 202010335871A CN 111415247 B CN111415247 B CN 111415247B
- Authority
- CN
- China
- Prior art keywords
- information
- default
- users
- neural network
- overdue
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Classifications
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a credit risk evaluation method after lending, a device, a storage medium and electronic equipment, wherein the method comprises the steps of collecting first information of first-class users with overdue and default behaviors in stock users, second information of the first-class users before overdue and default occur, and third information of the first-class users in overdue and default processes; performing data discretization on the first information and the second information of the first type of users, normalizing the third information and uniformly setting rule scores of the degree of default; the abstracted first information and second information are used as input data of the neural network, fourth information is obtained through the processing of the neural network, and training of the neural network is stopped when the difference value between the fourth information and the third information is smaller than a certain threshold value; the first information and the second information of all the stock users (all the stock users) are respectively input into a neural network, and the neural network outputs predicted default risk values of all the stock users; the risk of default of all users in stock is screened by setting a threshold value of warning risk of default and a threshold value of security of risk of default.
Description
Technical Field
The present invention relates to the field of information technologies, and in particular, to a method and apparatus for evaluating credit risk after credit, a storage medium, and an electronic device.
Background
The resident loan balance has grown greatly in recent years. As financial institutions, challenges to risk management at lending customers are also increasing. The accurate evaluation and control of overdue and default risks of the users can reduce the bad account rate of the financial institutions and improve the credit in a safe and steady mode.
Under the prior art, the financial institution dynamically evaluates the credit status of the user in a way of periodically inquiring credit information (such as credit report, public accumulation payment record, personal income tax record) of the user, and further analyzes overdue and default risks of the user. This periodic query behavior has the following drawbacks:
(1) Queries with too high a frequency can cause user aversion, which can easily lead to user churn.
(2) Overly frequent queries can result in significant increases in post-loan costs for the financial institution.
(3) The fixed period query mode is difficult to precisely and dynamically reflect the credit status of the user.
Disclosure of Invention
In order to solve the above problems, an object of an embodiment of the present invention is to provide a method, an apparatus, a storage medium, and an electronic device for evaluating credit risk after credit, which can dynamically and accurately evaluate credit risk after credit.
In a first aspect, an embodiment of the present invention provides a post-credit risk evaluation method, including:
collecting first information of a first type of users with overdue and default behaviors in stock users, second information of the first type of users before overdue and default occur, and third information of the first type of users when overdue and default processes occur;
performing data discretization on the first information and the second information of the first type of users, normalizing the third information and uniformly setting rule scores of the degree of default;
training a neural network model, inputting the abstracted first information and second information into a neural network, obtaining fourth information through the processing of the neural network, and stopping training of the neural network when the difference value between the fourth information and the third information is smaller than a certain threshold value;
respectively inputting first information and second information of all the stock of all the users into the neural network, and outputting predicted default risk values of all the stock of all the users by the neural network;
and screening the default risks of all the stock users by setting a default risk guard threshold and a default risk safety threshold.
In one possible implementation, the first information includes one or more of age information, occupation information, historical occupation information, working year information, native place information, and work place information.
In one possible implementation, the second information includes credit information, not limited to one or more of a total amount of loan, a balance of loan, an overdue amount, a first 12 months of a payment amount average, a payment amount variance, a payment amount maximum, a payment amount minimum, a first 12 months of a tax payment average, a tax payment amount variance, a tax payment amount maximum, or a tax payment amount minimum in the credit reporting.
In one possible implementation, the third information includes a timeout amount or an default amount.
In one possible implementation manner, when the default risk values of all the users in the stock are greater than the default risk alert threshold, the second information is collected by using a short-period query frequency, and the obtained second information is input into the neural network to obtain the latest default risk value.
In one possible implementation, when the risk value of the default of all the users in the stock is smaller than the security threshold value of the default risk, the second information is collected by using a long-period query frequency, and the obtained second information is input into the neural network to obtain the latest value of the default risk.
In a second aspect, an embodiment of the present invention further provides a post-credit risk evaluation device, including:
the data collection module is used for collecting first information of first-class users with overdue and default behaviors in stock users, second information of the first-class users before overdue and default occur, and third information of the first-class users when overdue and default processes occur;
the data abstraction module is used for carrying out data discretization on the first information and the second information of the first type of users, normalizing the third information and uniformly setting rule scores of the degree of default;
the model training module is used for taking the abstracted first information and second information as input data of a neural network, obtaining fourth information through processing of the neural network, and stopping training of the neural network when the difference value between the fourth information and the third information is smaller than a certain threshold value;
the model using module is used for respectively inputting first information and second information of all the stock users (all the stock users) into the neural network, and the neural network outputs predicted default risk values of all the stock users; and
and the screening module is used for screening the default risks of all the users in the stock by setting a default risk warning threshold and a default risk safety threshold.
In a third aspect, an embodiment of the present invention further provides a storage medium storing computer executable instructions for performing the above-described post-credit risk assessment method.
In a fourth aspect, an embodiment of the present invention further provides an electronic device, including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the post-credit risk assessment method described above.
According to the credit risk evaluation method, the credit risk evaluation device, the storage medium and the electronic equipment provided by the embodiment of the invention, through collection and induction of historical data, training of a neural network is performed by using an artificial intelligence technology, so that the credit risk evaluation method is formed, and the credit risk evaluation method is output as a system for accurately and dynamically evaluating the credit of the user, so that the default risk of the user can be truly, objectively and accurately described. Dynamic updating and differentiated management of user risks are achieved. For users with overdue and large default risks, the high-frequency information update can enable financial institutions to predict risks in advance and take actions, so that bad accounts are reduced to the greatest extent. For users with good credit, the low frequency information inquiry makes them feel better financial services.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for post-credit risk assessment provided by an embodiment of the invention;
FIG. 2 is a flowchart showing a method for evaluating risk of credit after credit according to an embodiment of the invention;
fig. 3 is a schematic structural diagram of an electronic device for performing the post-credit risk assessment method according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the invention is, therefore, to be taken in conjunction with the accompanying drawings, and it is to be understood that the scope of the invention is not limited to the specific embodiments.
In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Throughout the specification and claims, unless explicitly stated otherwise, the term "comprise" or variations thereof such as "comprises" or "comprising", etc. will be understood to include the stated element or component without excluding other elements or components.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
The embodiment of the invention provides a flow chart of a demand matching method, referring to FIG. 1 , The method comprises the following steps:
and (3) data collection: collecting first information (including but not limited to age, occupation, history occupation, working age, place of business, etc.) of a first class user of overdue and violating actions in the deposit users, second information (including credit information, not limited to total loan amount, loan balance, overdue amount in credit report, average value of the first 12 months of the deposit amount, variance of the deposit amount, maximum value of the deposit amount, minimum value of the deposit amount in the deposit amount record, average value of the first 12 months of the deposit amount in the tax record, variance of the deposit amount, maximum value of the deposit amount, minimum value of the deposit amount, etc.), and third information (overdue amount, violating amount, etc.) of the first class user when overdue occurs in overdue, violating processes.
Data abstraction: and performing data discretization on the first information and the second information of the first type of users. The first information may be fragmentation information of different data types of age, occupation, etc., such as occupation including teacher, worker, doctor, etc. Discretization means that it corresponds to discrete numbers, such as teacher-0, worker-1, doctor-2, respectively. Discretizing it would facilitate the deep learning network to calculate the gradient of data changes, facilitating its model training (normalized to between 0-1 for age, for age as an example, and for the highest age allowed to issue loans as an upper limit) (for occupation as an example, N occupation categories are represented as N-dimensional non-0, i.e., 1, vectors, each occupation represented by an N-th bit of 1, the remaining 0 vectors).
And normalizing the third information to uniformly characterize the severity of the offence. The direct data of the third information often corresponds to the overdue amount, credit score, etc. in the financial field. For neural networks, normalization is a technical method that facilitates model gradient transfer and convergence, which is itself prior art. And establishing a function mapping relation between the normalized data and direct data in the real financial field, so that the rule score of the normalized parameter can reflect the client condition in the direct data. Scoring by manually set rules is not limited to rules such as overdue amount greater than 5w, severity of 0.8; the overdue amount is greater than 10w, and the severity is 0.9; a complete violation, with a severity of 1.
Model training: the first information and the second information after the abstraction are used as input data of the neural network, and the process of the neural network is performed, wherein the process refers to a forward propagation stage (prior art) of the neural network, and can be analogically used as a function to an input condition to obtain an output result. But the processing procedure of the neural network is multi-node and multi-layer, belongs to a complex function, obtains fourth information (namely predicted user default severity), uses the third information to monitor, and trains the multi-layer deep neural network. The training error is the difference between the fourth information and the third information. And stopping training of the neural network when the training error is smaller than a certain threshold value.
Model use: when the neural network is used for predicting credit risk of the user, the first information and the second information of all the users (all the users) are respectively input into the neural network, and the output of the neural network, namely the fourth information, is the predicted default severity degree, namely the default risk value, of all the users. The process of inputting and outputting data is not innovative, and the prior art schemes can be listed here: multi-layer perceptron, support vector machine, recurrent neural network, etc.
And screening the predicted default risks of all users in the stock by setting a default risk warning threshold. The third class of users above the threshold are focused on in the following specific ways:
1) The second information is collected using a shorter period of query frequency.
2) And acquiring the latest second information, and inputting the latest second information into the neural network to obtain the latest default risk value.
And setting a default risk safety threshold value, and screening the default risks of all the predicted stock users. The attention frequency is reduced for the fourth class of users smaller than the threshold value by the following specific modes:
1) The second information is collected using a longer period of query frequency.
2) And acquiring the latest second information, and inputting the latest second information into the neural network to obtain the latest default risk value.
The flow of the matching method of the requirements is described in detail above, the method can also be realized by corresponding devices, and the structure and functions of the devices are described in detail below.
The embodiment of the invention also provides a credit risk evaluation device after credit, which comprises a data collection module, a data abstraction module, a model training module, a model using module and a screening module. Specifically:
the data collection module is used for collecting first information of first-class users with overdue and default behaviors in stock users, second information of the first-class users before overdue and default occur, and third information of the first-class users when overdue and default processes occur.
The data abstraction module is used for carrying out data discretization on the first information and the second information of the first type of users, normalizing the third information and uniformly setting rule scores for the degree of default.
The model training module is used for taking the abstracted first information and second information as input data of the neural network, obtaining fourth information through processing of the neural network, and stopping training of the neural network when the difference value between the fourth information and the third information is smaller than a certain threshold value.
The model using module is used for inputting first information and second information of all the stock users (all the stock users) into the neural network respectively, and the neural network outputs predicted default risk values of all the stock users.
The screening module is used for screening the default risks of all the users in the stock by setting a default risk warning threshold and a default risk safety threshold.
The present invention also provides a storage medium storing computer-executable instructions containing a program for performing the credit-after-credit risk assessment method described above, the computer-executable instructions being capable of performing the method of any of the method embodiments described above.
The storage medium may be any available medium or data storage device that can be accessed by a computer, including, but not limited to, magnetic storage (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical storage (e.g., CD, DVD, BD, HVD, etc.), and semiconductor storage (e.g., ROM, EPROM, EEPROM, nonvolatile storage (NAND FLASH), solid State Disk (SSD)), etc.
Fig. 3 shows a block diagram of an electronic device according to another embodiment of the invention. The electronic device 1100 may be a host server with computing capabilities, a personal computer PC, or a portable computer or terminal that is portable, etc. The specific embodiments of the present invention are not limited to specific implementations of electronic devices.
The electronic device 1100 includes at least one processor 1110, a communication interface (Communications Interface) 1120, a memory 1130, and a bus 1140. Wherein processor 1110, communication interface 1120, and memory 1130 communicate with each other through bus 1140.
The communication interface 1120 is used to communicate with network elements including, for example, virtual machine management centers, shared storage, and the like.
The processor 1110 is used to execute programs. The processor 1110 may be a central processing unit CPU, or an application specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention.
The memory 1130 is used for executable instructions. Memory 1130 may include high-speed RAM memory or non-volatile memory (nonvolatile memory), such as at least one magnetic disk memory. Memory 1130 may also be a memory array. Memory 1130 may also be partitioned and the blocks may be combined into virtual volumes according to certain rules. The instructions stored in memory 1130 may be executable by processor 1110 to enable processor 1110 to perform the post-credit risk assessment method of any of the method embodiments described above.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (5)
1. A method for post-credit risk assessment, comprising:
collecting first information of a first type of user with overdue and default behaviors in a deposit user, second information of the first type of user before overdue and default occur, and third information of the first type of user when overdue and default occur, wherein the first information comprises one or more of age information, occupation information, historical occupation information, working age information, local place information and work place information, the second information comprises credit information, and the second information comprises one or more of overdue amount or default amount in a credit report, and is not limited to loan total amount, loan balance, overdue amount average value of the first 12 months in a public accumulation payment record, payment amount variance, payment amount maximum value, payment amount minimum value, tax amount average value of the first 12 months in a tax payment record, payment amount variance, payment amount maximum value or tax amount minimum value, and the third information comprises overdue amount or default amount;
performing data discretization on the first information and the second information of the first type of users, normalizing the third information and uniformly setting rule scores of the degree of default;
training a neural network model, inputting the discretized first information and second information into a neural network, obtaining fourth information through the processing of the neural network, and stopping training of the neural network when the difference value between the fourth information and the third information is smaller than a certain threshold value;
respectively inputting first information and second information of all the stock of all the users into the neural network, and outputting predicted default risk values of all the stock of all the users by the neural network;
and screening the default risks of all the users of the stock by setting a default risk warning threshold value and a default risk safety threshold value, and when the default risk values of all the users of the stock are larger than the default risk warning threshold value, collecting the second information by using a short-period query frequency, and inputting the obtained second information into the neural network to obtain the latest default risk values.
2. The post-credit risk assessment method according to claim 1, wherein when the risk value of all the users of the stock against the offer is smaller than the risk safety threshold, the second information is collected using a long-period query frequency, and the obtained second information is input to the neural network to obtain the latest risk value against the offer.
3. A post-credit risk assessment apparatus, comprising:
the system comprises a data collection module, a credit collection module and a payment module, wherein the data collection module is used for collecting first information of a first type of users with overdue and default actions in stock users, second information of the first type of users before overdue and default actions occur, and third information of the first type of users when overdue and default actions occur, the first information comprises one or more of age information, professional information, historical professional information, working age information, land-by-land information and work place information, the second information comprises credit information, and the third information comprises overdue amount or default amount, the credit information is not limited to the total amount of loan, loan balance, overdue amount of overdue amount, the first 12 months of payment amount average value, payment amount variance, payment amount maximum value, payment amount minimum value, the first 12 months of tax payment amount average value, tax amount variance, tax payment amount maximum value or tax payment amount minimum value in a tax payment record in credit report;
the data abstraction module is used for carrying out data discretization on the first information and the second information of the first type of users, normalizing the third information and uniformly setting rule scores of the degree of default;
the model training module is used for taking the abstracted first information and second information as input data of a neural network, obtaining fourth information through processing of the neural network, and stopping training of the neural network when the difference value between the fourth information and the third information is smaller than a certain threshold value;
the model using module is used for respectively inputting first information and second information of all the stock users into the neural network, and outputting predicted default risk values of all the stock users of the neural network; and
and the screening module is used for screening the default risks of all the stock users by setting a default risk warning threshold value and a default risk safety threshold value, and when the default risk value of all the stock users is larger than the default risk warning threshold value, the second information is collected by using a short-period query frequency, and the obtained second information is input into the neural network to obtain the latest default risk value.
4. A storage medium having stored thereon computer executable instructions for performing the post-credit risk assessment method of any of claims 1-2.
5. An electronic device, comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions for execution by the at least one processor to enable the at least one processor to perform the post-credit risk assessment method of any one of claims 1-2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010335871.4A CN111415247B (en) | 2020-04-25 | 2020-04-25 | Post-credit risk evaluation method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010335871.4A CN111415247B (en) | 2020-04-25 | 2020-04-25 | Post-credit risk evaluation method and device, storage medium and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111415247A CN111415247A (en) | 2020-07-14 |
CN111415247B true CN111415247B (en) | 2023-07-28 |
Family
ID=71493683
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010335871.4A Active CN111415247B (en) | 2020-04-25 | 2020-04-25 | Post-credit risk evaluation method and device, storage medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111415247B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116452323B (en) * | 2023-04-28 | 2024-01-30 | 广州市良策网络技术有限公司 | Risk assessment method, system, equipment and storage medium |
CN117151869A (en) * | 2023-10-26 | 2023-12-01 | 北京信立合创信息技术有限公司 | Personal credit sign model and method based on deep learning |
CN117808578A (en) * | 2024-03-01 | 2024-04-02 | 杭银消费金融股份有限公司 | Intelligent pedestrian credit information data analysis method and system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5696907A (en) * | 1995-02-27 | 1997-12-09 | General Electric Company | System and method for performing risk and credit analysis of financial service applications |
WO2020037942A1 (en) * | 2018-08-20 | 2020-02-27 | 平安科技(深圳)有限公司 | Risk prediction processing method and apparatus, computer device and medium |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105550927A (en) * | 2015-11-30 | 2016-05-04 | 吉林大学 | Bank credit system risk assessment method and device |
CN107025596B (en) * | 2016-02-01 | 2021-07-16 | 腾讯科技(深圳)有限公司 | Risk assessment method and system |
US20180033009A1 (en) * | 2016-07-27 | 2018-02-01 | Intuit Inc. | Method and system for facilitating the identification and prevention of potentially fraudulent activity in a financial system |
US20180096426A1 (en) * | 2016-10-03 | 2018-04-05 | Bridgecare Finance, Inc. | System and method for providing and administering loans |
CN108389125B (en) * | 2018-02-27 | 2022-06-07 | 挖财网络技术有限公司 | Overdue risk prediction method and device for credit application |
CN109389486A (en) * | 2018-08-27 | 2019-02-26 | 深圳壹账通智能科技有限公司 | Loan air control rule adjustment method, apparatus, equipment and computer storage medium |
CN109255506B (en) * | 2018-11-22 | 2022-05-03 | 重庆邮电大学 | Internet financial user loan overdue prediction method based on big data |
CN110246029A (en) * | 2019-06-21 | 2019-09-17 | 深圳前海微众银行股份有限公司 | Risk management method, terminal, device and readable storage medium storing program for executing after loan |
CN110956273A (en) * | 2019-11-07 | 2020-04-03 | 中信银行股份有限公司 | Credit scoring method and system integrating multiple machine learning models |
-
2020
- 2020-04-25 CN CN202010335871.4A patent/CN111415247B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5696907A (en) * | 1995-02-27 | 1997-12-09 | General Electric Company | System and method for performing risk and credit analysis of financial service applications |
WO2020037942A1 (en) * | 2018-08-20 | 2020-02-27 | 平安科技(深圳)有限公司 | Risk prediction processing method and apparatus, computer device and medium |
Also Published As
Publication number | Publication date |
---|---|
CN111415247A (en) | 2020-07-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111415247B (en) | Post-credit risk evaluation method and device, storage medium and electronic equipment | |
US10943186B2 (en) | Machine learning model training method and device, and electronic device | |
Hensher et al. | An error component logit analysis of corporate bankruptcy and insolvency risk in Australia | |
US7904366B2 (en) | Method and system to determine resident qualifications | |
US10896462B2 (en) | System and method for aggregating and analyzing financial data | |
CN108648074A (en) | Loan valuation method, apparatus based on support vector machines and equipment | |
US20130332341A1 (en) | Systems and Methods for Monitoring and Optimizing Credit Scores | |
US20110166979A1 (en) | Connecting decisions through customer transaction profiles | |
JP2012504289A (en) | Evaluating loan access using online business transaction data | |
TW202004636A (en) | Insurance service optimization method and system and computer program product thereof | |
WO2019089990A1 (en) | Entity segmentation for analysis of sensitivities to potential disruptions | |
WO2021138271A1 (en) | Creating predictor variables for prediction models from unstructured data using natural language processing | |
WO2019021314A1 (en) | A system and method for default probability prediction and credit scoring framework | |
US20050171885A1 (en) | Object oriented demographically predictive insurance agency asset evaluation system and method | |
CN111369345A (en) | Big data credit user credit assessment method and system of cloud computing block chain | |
US8131635B2 (en) | Method and system to manage a credit portfolio and to trigger credit actions | |
US10636044B2 (en) | Projecting resource demand using a computing device | |
CN113220447B (en) | Financial wind control system and method based on edge calculation | |
AU2022360356A1 (en) | Data compression techniques for machine learning models | |
CN115689571A (en) | Abnormal user behavior monitoring method, device, equipment and medium | |
US11631144B2 (en) | Crowdfunding endorsement using non-internet enabled devices | |
RU2717903C1 (en) | Automated system for modelling changes in information space content | |
US11625788B1 (en) | Systems and methods to evaluate application data | |
Mitra | Scenario generation for operational risk | |
CN111915425A (en) | Loan approval method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |