CN114626938A - Intelligent decision engine, decision system and decision method - Google Patents
Intelligent decision engine, decision system and decision method Download PDFInfo
- Publication number
- CN114626938A CN114626938A CN202210301109.3A CN202210301109A CN114626938A CN 114626938 A CN114626938 A CN 114626938A CN 202210301109 A CN202210301109 A CN 202210301109A CN 114626938 A CN114626938 A CN 114626938A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- information
- decision
- prediction
- 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.)
- Pending
Links
Images
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
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Abstract
The invention discloses an intelligent decision engine, a decision system and a decision method, and relates to the technical field of computer decision systems. The decision engine of the present invention comprises the following modules: the initialization module is used for initializing the data of the whole decision engine; the data processing module is used for processing the information input by the user; the default prediction module is used for predicting default according to the new data input by the user and outputting a prediction result; the model management module is used for training a new training model for the training model in the default prediction module and managing the model version; a decision engine database. The method predicts various types and ways of data and information received from the client based on the training model, has more comprehensive reference information data, adopts default risk results automatically given by the training model based on the decision engine, and has high accuracy and efficiency and strong decision evaluation objectivity.
Description
Technical Field
The invention belongs to the technical field of computer decision-making systems, and particularly relates to an intelligent decision-making engine for loan payment, a decision-making system for loan payment and a decision-making method for loan payment.
Background
The loan is generally a loan for a money unit or a person, such as a bank, a credit union and the like, and generally stipulates interest and repayment date; the general loan is an assembly for loan, cash, overdraft and the like, and a bank puts in concentrated currency and currency funds in a loan mode, so that the requirement of social expanded reproduction on fund supplementation can be met, and the economic development is promoted.
The general flow of the loan includes: (1) in the loan application stage, a client needs to apply for a loan institution such as a bank and fill in some application data; (2) in the loan auditing stage, the borrower needs to audit application data submitted by a borrower; (3) signing a loan contract, and after the approval is passed, both parties sign the loan contract and guarantee the same, according to the specific situation; (4) and issuing a loan.
In the whole loan process, the auditing decision of the loan is the most important link, whether the auditing decision is right or not is directly related to the problem of credit risk, the existing loan process, particularly the mortgage-free loan process, still adopts manual auditing, and auditors carry out systematic investigation and investigation on the qualification, credit and property conditions of a loan subject according to credit investigation reports; in practice, for the auditing and decision-making of the loan process, the relevant lending personnel usually only pay attention to the identification of documents, but lack the judgment and decision-making of the whole materials and data, which easily causes the fraud in the loan process and causes the risk of credit.
The existing loan approval has the following problems: (1) the method is low in penetration degree based on the angle of the Internet technology, the approval wind control levels are different, the auditing is mostly carried out in a manual traditional mode, the application and assistance of the Internet technology are lacked, and the auditing efficiency cannot meet the actual business requirements; (2) survey data acquired by traditional loan auditing cannot be communicated with an approval system, audit data cannot be uniformly stored, and data are difficult to call in a later period; (3) the data island condition of the loan industry is common, a sharing mechanism is lacked, information among financial institutions is difficult to share, and the condition of omission is easily caused to the risk of loan default. Therefore, in order to solve the above problems, it is of great practical significance to provide an intelligent decision engine, a decision system and a decision method.
Disclosure of Invention
The invention provides an intelligent decision engine, a decision system and a decision method, which solve the problems.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention provides an intelligent decision engine which is provided for a service end in an SDK form and embedded into a loan system, and comprises:
an initialization module: the method comprises the steps of initializing data of the whole decision engine, specifically comprising creating a decision engine instance and a model instance; the creation decision engine instance is used for selecting a specific corresponding decision engine instance for subsequent decision actions of corresponding loan personnel based on the decision engine instance; the model creating example is to select a specific corresponding training model for training subsequent input data;
A data processing module: the system is used for processing the information input by the user, including data acquisition and data cleaning; the data acquisition is used for acquiring interface data of data input by a loan system end user; the data cleaning is used for judging the correctness and normalization of the acquired data, carrying out exception prompting on the data which do not meet the requirements, automatically modifying the data into the data which meet the requirements in a standardized format by a capturing and identifying program, then recording the data, and automatically supplementing the lacking information;
a default prediction module: the system comprises a data processing module, a default prediction module and a decision suggestion module, wherein the data processing module is used for carrying out default prediction according to new data input by a user and outputting a prediction result, a training model in a file is read before prediction, the training model is trained and stored by the training module, after the training model is read, data read in by the data processing module can be transmitted into the default prediction module formed after the training of the training model, the prediction result is returned to the user after the prediction of the default prediction module, the decision result of whether the loan of the user is possible to be default is given, and the decision suggestion of whether the loan is allowed to be placed is given based on the decision result;
a model management module: the system is used for optimizing and iterating the training model in the default prediction module and managing the model version;
Decision engine database: the decision process for the decision engine provides data storage and support, and the stored data comprises default prediction model information, model parameter information, model evaluation information, model prediction result information and prediction data information.
Further, the training module comprises a primary learner and a secondary learner, the primary learner takes a training set and classification attributes as the input of the primary learner, then an XGboost composite tree model is constructed according to the output of the primary learner as the input of the secondary learner, and finally a learning model is obtained and predicted.
Further, the primary learner includes Logitics regression, support vector machine, random forest, neural network.
Further, the workflow of the intelligent decision engine is:
model training and corresponding evaluation result training: acquiring original data for prediction, cleaning the original data by using a data processing module to obtain model data meeting requirements and standards, and then training based on a training module according to the acquired model data to obtain a corresponding training model and a model evaluation result corresponding to the training model;
actual prediction: the method comprises the steps of obtaining user original data needing to be predicted, selecting a corresponding training model and a decision engine instance for subsequent prediction actions by using an initialization module, cleaning the original data by using a data processing module to obtain model data meeting requirements and standards, using the model data to perform actual prediction, returning a predicted result to a user after the model data is predicted by a default prediction module, giving a judgment result of whether the loan of the user is possible to be default, and giving a decision suggestion of whether to approve loan release based on the judgment result.
Further, the original data comprises personal basic information, bank credit information, unit credit information, real estate information, vehicle estate information and network search information corresponding to the customer filled by the user; the network inquiry information is inquired by the business information network, the court information comprehensive inquiry network and the crime information inquiry network based on the customer name, the identification card number, the mobile phone number and the work order.
A decision system, the above intelligent decision engine implementation, comprising:
an intelligent decision engine;
support layer: the system is connected with an intelligent decision engine, provides input and access of data required by client loan approval for the intelligent decision engine, and comprises a platform interface for inputting personal basic information and unit credit investigation information of a client and accessing a corresponding credit investigation system, house property information, vehicle property information and network investigation information, and is used for a user to realize the operation of client loan information and a terminal with login authority verification;
a logic layer: program code and functional structures associating the support layer with the intelligent decision engine.
An intelligent decision-making method implemented by the decision-making system as claimed in claim 6, comprising the steps of:
S1, the user uses a terminal login decision system based on authorized login authority to fill in personal basic information and unit credit investigation information of the client needing loan risk default evaluation, and selects a credit investigation system, house property information, vehicle property information and a network investigation information platform needing to be connected and grabbed, and automatically grabs corresponding original data information;
s2, selecting a corresponding training model and a decision engine instance for a subsequent prediction action by utilizing an initialization module for the obtained original data needing prediction, cleaning the original data by utilizing a data processing module to obtain model data meeting requirements and standards, and performing actual prediction by utilizing the model data;
and S3, returning the predicted result to the user through the terminal after the default prediction module predicts the default result, displaying the result on the terminal, giving the result to the user to judge whether the loan is possible to default, and giving decision opinions of whether to approve lending or not based on the judgment result.
Compared with the prior art, the invention has the following beneficial effects:
the method and the system predict various data and information of multiple types and multiple ways corresponding to the received customers based on the trained model, reference information data are wide and comprehensive, the trained model automatically gives a default risk result based on the decision engine instead of manually judging the default risk, the reference range of the decision-making data is wide, the accuracy and the efficiency are high, the decision-making evaluation objectivity is high, the interference of human factors is avoided, the method and the system are favorable for lending auditors to accurately, efficiently, comprehensively and quickly make preliminary judgment on the default risk of borrowers, and the method and the system are automatically realized based on a computer instead of manual evaluation, so that the decision-making efficiency is greatly improved.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of an intelligent decision engine according to the present invention;
FIG. 2 is an architecture diagram of a decision system based on an intelligent decision engine according to the present invention;
FIG. 3 is a diagram illustrating the steps of a decision method based on a decision system according to the present invention;
FIG. 4 is a diagram illustrating training steps and a schematic diagram corresponding to a training module according to the present invention;
FIG. 5 is a flow chart of model training and training of corresponding evaluation results according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an intelligent decision engine of the present invention, provided to a service end in the form of SDK, embedded in a loan system, includes:
an initialization module: the method comprises the steps of initializing data of the whole decision engine, specifically comprising creating a decision engine instance and a model instance; creating a decision engine instance, namely selecting a specific corresponding decision engine instance for a subsequent decision action on a corresponding borrower based on the decision engine instance; the model instance is created by selecting a specific corresponding training model for training subsequent input data;
a data processing module: the system is used for processing the information input by the user, including data acquisition and data cleaning; the data acquisition is used for acquiring interface data of data input by a loan system end user; the data cleaning is used for judging the correctness and normalization of the acquired data, carrying out exception prompting on the data which does not meet the requirements, automatically modifying the data into the data which meets the requirements and has a standardized format by a capturing and identifying program, then recording the data, and automatically supplementing the lacking information;
a default prediction module: the system comprises a data processing module, a default prediction module and a decision suggestion module, wherein the data processing module is used for carrying out default prediction according to new data input by a user and outputting a prediction result, a training model in a file is read before prediction, the training model is trained and stored by the training module, after the training model is read, data read in by the data processing module can be transmitted into the default prediction module formed after the training of the training model, the prediction result is returned to the user after the prediction of the default prediction module, the decision result of whether the loan of the user is possible to be default is given, and the decision suggestion of whether the loan is allowed to be placed is given based on the decision result;
A model management module: the new training model is used for training the training model in the default prediction module and managing the model version;
decision engine database: the decision process for the decision engine provides data storage and support, and the stored data comprises default prediction model information, model parameter information, model evaluation information, model prediction result information and prediction data information; the prediction model information is specifically that after model training, a generated model file is stored and predicted in a model table, and the model file comprises a model version number, training time, a parameter id, a model evaluation result id and a mold core file; the model parameter information is specifically model parameters required for storing and training the model based on the form of a prediction model parameter table, and comprises model parameter id, creation time, a logistic regression parameter file, a support vector machine parameter file, a random forest parameter file, a neural network parameter file and an xgboost model parameter file; the model prediction result information is stored in a form of a prediction result storage table, and comprises a prediction number, data id, a model version number, prediction time and a prediction result; the basic information of the client stored in the form of a client table, including the client number, name, sex, contact telephone number and order number, is also included in the raw data.
As shown in fig. 4, the training module includes a primary learner and a secondary learner, the primary learner uses the training set and the classification attributes as the input of the primary learner, and then constructs an XGBoost composite tree model according to the output of the primary learner as the input of the secondary learner, and finally obtains and predicts the learning model.
The primary learner comprises Logitics regression, a support vector machine, a random forest and a neural network.
As shown in fig. 5, the workflow of the intelligent decision engine is:
model training and corresponding evaluation result training: acquiring original data for prediction, cleaning the original data by using a data processing module to obtain model data meeting requirements and standards, and then training based on a training module according to the acquired model data to obtain a corresponding training model and a model evaluation result corresponding to the training model;
actual prediction: the method comprises the steps of obtaining user original data needing to be predicted, selecting a corresponding training model and a decision engine instance for subsequent prediction actions by using an initialization module, cleaning the original data by using a data processing module to obtain model data meeting requirements and standards, using the model data to perform actual prediction, returning a predicted result to a user after the model data is predicted by a default prediction module, giving a judgment result of whether the loan of the user is possible to be default, and giving a decision suggestion of whether to approve loan release based on the judgment result.
The original data comprises personal basic information, bank credit information, unit credit information, house property information, vehicle property information and network search information corresponding to the customer filled by the user; the network inquiry information is the information which is inquired outside the listed ways based on the client name, the identity card number, the mobile phone number and the work order in the industry and commerce information network, the court information comprehensive inquiry network and the crime information inquiry network.
As shown in fig. 2, a decision system implemented by the intelligent decision engine as described above includes:
an intelligent decision engine;
support layer: the system is connected with an intelligent decision engine, provides input and access of data required by client loan approval for the intelligent decision engine, and comprises a platform interface for inputting personal basic information and unit credit investigation information of a client and accessing a corresponding credit investigation system, house property information, vehicle property information and network investigation information, and is used for a user to realize the operation of client loan information and a terminal with login authority verification;
a logic layer: program code and functional structures associating the support layer with the intelligent decision engine.
As shown in fig. 3, an intelligent decision method implemented by using the decision system described above includes the following steps:
S1, the user uses a terminal login decision system based on authorized login authority to fill in personal basic information and unit credit investigation information of the client needing loan risk default evaluation, and selects a credit investigation system, house property information, vehicle property information and a network investigation information platform needing to be connected and grabbed, and automatically grabs corresponding original data information;
s2, selecting a corresponding training model and a corresponding decision engine instance for a subsequent prediction action by utilizing an initialization module for the obtained original data needing prediction, cleaning the original data by utilizing a data processing module to obtain model data meeting requirements and standards, and performing actual prediction by utilizing the model data;
and S3, returning the predicted result to the user through the terminal after the default prediction module predicts the default result, displaying the result on the terminal, giving the result of judging whether the loan is possible to default to the user, and giving decision-making opinions whether to approve loan placement based on the judgment result.
Has the beneficial effects that:
the method and the system predict various data and information of multiple types and multiple ways corresponding to the client based on the trained model, reference information data are wide and comprehensive, the trained model automatically gives out default risk results based on the decision engine instead of manually judging the default risk, the decision is wide in reference range, high in accuracy and efficiency according to the data, strong in decision evaluation objectivity, interference of human factors is avoided, accurate, efficient, comprehensive and rapid preliminary judgment on the default risk of loan officers is facilitated for loan officers, and the efficiency of decision is greatly improved based on automatic realization of a computer instead of manual evaluation.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand the invention for and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (7)
1. An intelligent decision engine, provided to a service in the form of an SDK, embedded in a loan system, comprising:
an initialization module: the method comprises the steps of initializing data of the whole decision engine, specifically comprising creating a decision engine instance and a model instance; the creation decision engine instance is used for selecting a specific corresponding decision engine instance for carrying out a decision action on a corresponding loan person based on the decision engine instance; the model creating example is to select a specific corresponding training model for training subsequent input data;
A data processing module: the system is used for processing the information input by the user, including data acquisition and data cleaning; the data acquisition is used for acquiring interface data of data input by a loan system end user; the data cleaning is used for judging the correctness and normalization of the acquired data, carrying out exception prompting on the data which do not meet the requirements, automatically modifying the data into the data which meet the requirements in a standardized format by a capturing and identifying program, then recording the data, and automatically supplementing the lacking information;
a default prediction module: the system comprises a data processing module, a default prediction module and a decision suggestion module, wherein the data processing module is used for carrying out default prediction according to new data input by a user and outputting a prediction result, a training model in a file is read before prediction, the training model is trained and stored by the training module, after the training model is read, data read in by the data processing module can be transmitted into the default prediction module formed after the training of the training model, the prediction result is returned to the user after the prediction of the default prediction module, the decision result of whether the loan of the user is possible to be default is given, and the decision suggestion of whether the loan is allowed to be placed is given based on the decision result;
a model management module: the system is used for optimizing and iterating the training model in the default prediction module and managing the model version;
Decision engine database: the decision process for the decision engine provides data storage and support, and the stored data comprises default prediction model information, model parameter information, model evaluation information, model prediction result information and prediction data information.
2. An intelligent decision engine as claimed in claim 1, wherein the training module comprises a primary learner and a secondary learner, the primary learner uses a training set and classification attributes as inputs of the primary learner, and then constructs an XGboost composite tree model according to an output of the primary learner as an input of the secondary learner, and finally obtains and predicts a learning model.
3. An intelligent decision engine as claimed in claim 2, wherein the primary learner comprises logistic regression, support vector machine, random forest, neural network.
4. An intelligent decision engine according to claim 1, characterized in that the workflow of the intelligent decision engine is:
model training and corresponding evaluation result training: acquiring original data for prediction, cleaning the original data by using a data processing module to obtain model data meeting requirements and standards, and then training based on a training module according to the acquired model data to obtain a corresponding training model and a model evaluation result corresponding to the training model;
Actual prediction: the method comprises the steps of obtaining user original data needing to be predicted, selecting a corresponding training model and a decision engine instance for subsequent prediction actions by using an initialization module, cleaning the original data by using a data processing module to obtain model data meeting requirements and standards, using the model data to perform actual prediction, returning a predicted result to a user after prediction by a default prediction module, giving a judgment result of whether loan of the user is possible to be default, and giving a decision suggestion of whether loan is agreed based on the judgment result.
5. An intelligent decision engine according to claim 4, wherein the raw data includes personal basic information, bank credit information, unit credit information, property information, vehicle property information and network check information corresponding to the customer filled by the user; the network inquiry information is inquired outside the listed ways of an industrial and commercial information network, a court information comprehensive inquiry network and a crime information inquiry network based on the client name, the identity card number, the mobile phone number and the work order.
6. A decision making system implemented using the intelligent decision engine of any of claims 1-5, comprising:
An intelligent decision engine;
support layer: the system is connected with an intelligent decision engine, provides input and access of data required by client loan approval for the intelligent decision engine, and comprises a platform interface for inputting personal basic information and unit credit investigation information of a client and accessing a corresponding credit investigation system, house property information, vehicle property information and network investigation information, and is used for a user to realize the operation of client loan information and a terminal with login authority verification;
a logic layer: program code and functional structures associating the support layer with the intelligent decision engine.
7. An intelligent decision-making method implemented by the decision-making system as claimed in claim 6, comprising the steps of:
s1, the user uses a terminal login decision system based on authorized login authority to fill in personal basic information and unit credit investigation information of the client needing loan risk default evaluation, and selects a credit investigation system, house property information, vehicle property information and a network check information platform needing to be connected and grabbed, and automatically grabs corresponding original data information;
s2, selecting a corresponding training model and a corresponding decision engine instance for a subsequent prediction action by utilizing an initialization module for the obtained original data needing prediction, cleaning the original data by utilizing a data processing module to obtain model data meeting requirements and standards, and performing actual prediction by utilizing the model data;
And S3, returning the predicted result to the user through the terminal after the default prediction module predicts the default result, displaying the result on the terminal, giving the result to the user to judge whether the loan is possible to default, and giving decision opinions of whether to approve lending or not based on the judgment result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210301109.3A CN114626938A (en) | 2022-03-25 | 2022-03-25 | Intelligent decision engine, decision system and decision method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210301109.3A CN114626938A (en) | 2022-03-25 | 2022-03-25 | Intelligent decision engine, decision system and decision method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114626938A true CN114626938A (en) | 2022-06-14 |
Family
ID=81903786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210301109.3A Pending CN114626938A (en) | 2022-03-25 | 2022-03-25 | Intelligent decision engine, decision system and decision method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114626938A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436718A (en) * | 2023-10-06 | 2024-01-23 | 纬创软件(武汉)有限公司 | Intelligent data management platform based on multidimensional engine |
| CN117436718B (en) * | 2023-10-06 | 2024-05-14 | 纬创软件(武汉)有限公司 | Intelligent data management platform based on multidimensional engine |
-
2022
- 2022-03-25 CN CN202210301109.3A patent/CN114626938A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436718A (en) * | 2023-10-06 | 2024-01-23 | 纬创软件(武汉)有限公司 | Intelligent data management platform based on multidimensional engine |
| CN117436718B (en) * | 2023-10-06 | 2024-05-14 | 纬创软件(武汉)有限公司 | Intelligent data management platform based on multidimensional engine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Siddiqi | Intelligent credit scoring: Building and implementing better credit risk scorecards | |
| Sadok et al. | Artificial intelligence and bank credit analysis: A review | |
| Chan et al. | Determinants of mortgage default and consumer credit use: the effects of foreclosure laws and foreclosure delays | |
| Eze et al. | Electronic banking and profitability of commercial banks in Nigeria | |
| CN110472815B (en) | Risk control method and system for financing enterprise in supply chain financial business | |
| Aduda et al. | The relationship between credit scoring practices by commercial banks and access to credit by small and medium enterprises in Kenya | |
| CN115271912A (en) | Credit business intelligent wind control approval system and method based on big data | |
| Zhang et al. | A study on SMIE credit evaluation model based on blockchain technology | |
| CN115063233A (en) | Method, system and device for realizing banking business service process | |
| CN114862110A (en) | Method and device for building middle platform of commercial banking business, electronic equipment and storage medium | |
| Ways | and Machine Learning | |
| Biswas et al. | Automated credit assessment framework using ETL process and machine learning | |
| Darapaneni et al. | Loan prediction software for financial institutions | |
| Wagdi et al. | The integration of big data and artificial neural networks for enhancing credit risk scoring in emerging markets: Evidence from Egypt | |
| CN115564591A (en) | Financing product determination method and related equipment | |
| CN114626938A (en) | Intelligent decision engine, decision system and decision method | |
| CN113743816A (en) | Vehicle rental risk control method and device, computer equipment and storage medium | |
| US20230186385A1 (en) | Computer-implemented system and method of facilitating artificial intelligence based lending strategies and business revenue management | |
| Lin et al. | Research on Credit Big Data Algorithm Based on Logistic Regression | |
| Rismawati et al. | Environmental performance, Islamic corporate governance, and liquidity's impact on financial performance with sustainability reporting as a mediating factor | |
| Alma et al. | Strategic decision making of micro-lenders: An innovative business model for risk management | |
| US20240013582A1 (en) | Digital twin based vehicle evaluation engine | |
| Goyal et al. | Creditworthiness Assessment Using Natural Language Processing | |
| Iqbal | Measuring credit risk in a quantitative way for countryside microfinance institutions: Case study of China | |
| KR20170004934A (en) | System and Method for Real time based Credit Risk Analysis using the Integrated Account Information |
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 |