Client credit qualification prediction method and related equipment
By preprocessing and feature extraction of customer credit information data, combined with qualification evaluation and model training, accurate prediction of future customer qualification changes is achieved, and the problem of difficult to predict future customer qualification changes in existing technology is solved, and the credit risk of financial institutions is reduced.
Patent Information
- Application Number
- CN202411584848.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-07
- Publication Date
- 2025-03-11
AI Technical Summary
The existing technology is difficult to accurately predict future customer qualification changes, resulting in financial institutions facing greater credit risks.
By collecting customer credit information data, performing data preprocessing and qualification feature extraction, using qualification classification standards to conduct two-stage qualification evaluation, training classification models to generate qualification prediction models, and then predicting future customer qualification changes.
It realizes accurate predictions of future customer qualification changes, helps financial institutions identify customers with better qualifications in the future, reduce credit risks, and provide more scientific and accurate decision-making basis.
Smart Images
Figure CN119599781A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure generally relates to the field of artificial intelligence technology, and specifically relates to a method, device, electronic device, computer-readable storage medium, and computer program product for predicting customer credit qualifications. Background Art
[0002] In the field of financial credit, accurate assessment of customer qualifications is of great significance for risk control and credit limit determination.
[0003] Traditional credit assessment includes analysis of customers' historical financial data and social network login information, as well as the use of data mining and machine learning techniques to collect and organize large amounts of data to establish a credit scoring model, thereby discovering the connections and patterns between data through analysis and mining of massive data. In addition, intelligent risk control models can be established through deep learning and neural networks to reduce human interference, and high-security and high-reliability credit assessment solutions can be established through blockchain.
[0004] Although there are many methods available for assessing client qualifications, the client's own financial status is constantly changing. The changing financial status makes it difficult for financial institutions to identify the client, resulting in a significant increase in credit risk.
[0005] Therefore, how to reduce the credit risk of financial institutions is an urgent problem to be solved. Summary of the invention
[0006] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a method, device, electronic device, computer-readable storage medium and computer program product for predicting customer credit qualifications, so as to predict changes in customer qualifications in the future and reduce the credit risk of financial institutions.
[0007] In a first aspect, an embodiment of the present application provides a method for predicting customer credit qualifications, comprising:
[0008] Collect credit information data of each customer, extract qualification features after data preprocessing, and obtain feature data;
[0009] According to the characteristic data, the user's qualifications are evaluated in the first and second stages according to the qualification classification standard to obtain the qualification level; wherein the second stage is later than the first stage and later than the credit granting stage;
[0010] Training a classification model based on the changes in qualification levels in the first stage and the second stage to generate a qualification prediction model;
[0011] Receive the target customer's credit information data, call the qualification prediction model to predict the user's future qualifications, and obtain an output result.
[0012] In one embodiment, before calling the qualification prediction model to predict the user's future qualifications, the method further includes:
[0013] Assess the qualification level of the target customer in the first stage as the target first level;
[0014] Determining whether the target first level is optimal;
[0015] If so, output the result that the target customer is currently the best qualified customer.
[0016] In one embodiment, the credit information data includes at least two of: personal information, income data, asset data, credit data, transaction records, and social network information.
[0017] In one embodiment, the second stage is the third month after the loan is disbursed.
[0018] In one embodiment, the training of the classification model according to the change of qualification levels in the first stage and the second stage includes:
[0019] Set different parameters for multiple pre-built classification models to obtain multiple models to be trained;
[0020] According to the change of qualification level in the first stage and the second stage, each of the models to be trained is trained respectively, and the prediction index of the trained models is evaluated;
[0021] According to the prediction index, an optimal model is determined from multiple trained models as a qualification prediction model.
[0022] In one embodiment, after obtaining the output result, the method further includes:
[0023] Identify whether the output result is that the qualification has improved;
[0024] If so, the target customer and related customer information are output.
[0025] In a second aspect, an embodiment of the present application provides a device for predicting customer credit qualifications, including:
[0026] The data processing unit is used to collect credit information data of each customer, extract qualification features after data preprocessing, and obtain feature data;
[0027] A feature evaluation unit, configured to perform a first-stage and a second-stage user qualification evaluation on the user according to the feature data and by using a qualification classification standard to obtain a qualification level; wherein the second stage is later than the first stage and later than the credit granting stage;
[0028] A classification training unit, used to train a classification model according to the changes in the qualification levels in the first stage and the second stage, and generate a qualification prediction model;
[0029] The qualification prediction unit is used to receive the credit information data of the target customer, call the qualification prediction model to predict the user's future qualifications, and obtain an output result.
[0030] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the embodiment of the present application when executing the program.
[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the embodiment of the present application.
[0032] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements the method described in the embodiment of the present application when executed by a processor.
[0033] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:
[0035] Figure 1 A schematic diagram of a process flow of a method for predicting customer credit qualifications provided by an embodiment of the present application is shown;
[0036] Figure 2 A schematic diagram of credit qualification improvement provided by an embodiment of the present application is shown;
[0037] Figure 3 An exemplary structural block diagram of a device for predicting customer credit qualifications provided in an embodiment of the present application is shown;
[0038] Figure 4 The overall structure diagram of the customer credit qualification prediction device provided by the embodiment of the present application is shown;
[0039] Figure 5 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION
[0040] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.
[0041] It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the drawings and in combination with the embodiments. Although the embodiments of the present application provide the method operation instruction steps shown in the following embodiments or drawings, more or fewer operation instruction steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiments of the present application. The method may be executed in the order of the methods shown in the embodiments or drawings or in parallel during the actual processing process or when the device is executed.
[0042] It should also be noted that the acquisition or use of data in the embodiments of the present application requires the user's consent. The relevant data can only be obtained after the user's authorization and permission, and the acquisition or use of the data complies with relevant legal provisions.
[0043] In the field of financial credit, for financial institutions and banks, accurate assessment of customer qualifications plays an extremely important role in the overall risk control and other financial strategies of the institution. Although there are many methods for evaluating customer qualifications, none of the existing methods realize the value of changes in customer qualifications in the future to the operation of financial institutions, and there is no method to predict changes in customer qualifications in the future. For financial institutions, especially customers whose qualifications will improve in the future, they have higher operating value. By providing better operating strategies in advance, such as better credit interest rates and credit limits, etc., the credit utilization rate and repurchase rate of customers can be increased, thereby improving the operating capacity of financial institutions.
[0044] This application proposes a customer credit qualification prediction method, which aims to predict the customer's future qualification changes through an algorithm model, identify the customer's credit status in advance, and thus help identify customers whose qualifications will improve in the future, provide financial institutions with a more scientific and accurate basis for decision-making, and reduce credit risks. Figure 1 , Figure 1 FIG. 1 is a flow chart showing a method for predicting customer credit qualifications provided by an embodiment of the present application. Figure 1 As shown, the method includes:
[0045] S101, collecting credit information data of each customer, extracting qualification features after data preprocessing, and obtaining feature data;
[0046] Collect users' personal information, income data, asset data, credit data, transaction records, social network information and other related credit information data. You can choose at least two to implement multi-dimensional analysis. There is no limitation on the type of specific credit information data collected. It can be set according to the actual analysis accuracy requirements.
[0047] The collected raw credit information data is preprocessed to improve data quality and the accuracy of subsequent data analysis. The specific data preprocessing method can refer to the relevant technology and is not limited here. The corresponding data preprocessing method can be selected according to the type of credit information data collected. To deepen understanding, a data preprocessing process is proposed here, which can specifically include the following means: 1. Data cleaning. (1) Remove duplicate data: Check and delete duplicate records in the data set to ensure the uniqueness of each user's data. (2) Process missing values: For missing data, select appropriate filling methods according to data characteristics and business scenarios, such as mean filling, median filling, mode filling or use machine learning algorithms for predictive filling. (3) Process outliers: Detect and process outliers in the data, and remove or correct outliers in the sample. 2. Data integration. Integrate data from different data sources according to user ID or other unique identifiers to form a unified user data table, ensuring that the data format, unit, etc. between different data sources are consistent for subsequent analysis. 3. Data standardization. For numerical data, standardization is performed to eliminate the dimensional differences between different features to make the model easier to learn. The standardization methods that can be used here include Z-score standardization, Min-Max standardization, etc. 4. Data encoding. For categorical data (such as gender, occupation, etc.), encode it and convert it into numerical data so that the model can process it. Depending on the data, you can use one-hot encoding (One-Hot Encoding), label encoding (Label Encoding) and other methods for encoding.
[0048] It should be noted that, in this embodiment, only the above preprocessing process is introduced as an example, and other preprocessing means taken according to different data processing needs can refer to the above preprocessing process, which will not be repeated here.
[0049] Extract features related to user qualifications, such as credit history, income level, debt status, etc., from the preprocessed data for subsequent qualification feature analysis.
[0050] S102, based on the characteristic data, the user's qualification evaluation is performed in the first and second stages according to the qualification classification standard to obtain the qualification level;
[0051] There is no limitation on the specific qualification classification standards adopted. Different financial institutions can set corresponding standards based on the actual credit product needs and use different dimensions for comprehensive assessment. For example, comprehensive analysis of personal information and basic qualifications, including age, marital status, education level, occupation and economic income, credit record, assets, liabilities, etc., and divide users into different levels through a set of qualification classification standards.
[0052] In this application, the user qualification evaluation is performed in the first and second stages, wherein the second stage is later than the first stage and later than the credit granting stage, i.e., the user qualification is evaluated again in the second stage after the credit granting, in order to train the classification model for prediction based on the customer characteristics in the second stage after the credit granting. Optionally, the second stage is the third month after the loan is issued (mob3).
[0053] The first stage can be before credit is granted or during credit granting. It should be earlier than the second stage but should be no later than the credit granting stage in order to measure the credit qualifications of the customers before or during credit granting, so as to make comparative analysis and prediction with the qualifications after credit granting in the second stage.
[0054] Taking the first stage as the credit granting stage and the second stage as the third month after the loan is issued as an example, for the same user, the qualification classification of the credit granting stage and the qualification classification of mob3 are obtained, such as Figure 2 As shown, the label of users whose mob3 qualifications have improved compared to those in the credit granting stage is 1, which is marked with a black arrow in the figure, and the labels of other users are 0. Assuming that the user qualifications are divided into A, B, C, and D, where A is better than B, better than C, and better than D, then for users whose qualification in the credit granting stage is C, if mob3's qualification is A or B, the label is 1, and if mob3's qualification is C or D, the label is 0. Among them, users whose credit stratum is A are already the stratum with the best qualifications and there is no possibility of improvement. Optionally, they can be removed during data collection and not included in the training set to reduce the amount of data analysis. Of course, they can also be retained, and there is no limitation here.
[0055] S103, training a classification model according to the changes in qualification levels in the first and second stages to generate a qualification prediction model;
[0056] The training of the qualification prediction model belongs to a 0-1 classification task, and a variety of classification models can be used, such as logistic regression, support vector machine, deep neural network, etc. Optionally, the classification model can use the xgboost (an integrated learning algorithm based on gradient boosting tree) model, which has multiple hyperparameters, such as learning rate, number of trees, maximum depth of trees, etc., and has the advantages of high performance and strong interpretability. In this embodiment, only the xgboost model is used as an example for introduction, and other model types can refer to the introduction of this embodiment, which will not be repeated here.
[0057] In the model training stage, the training set is divided into m parts. Specifically, the k-cross validation method can be used to divide the training set, which is not limited here. Take m-1 parts as the training set and the remaining part as the validation set. Put the data into the classification model for training, and finally the trained model is used as the qualification prediction model.
[0058] Optionally, in order to improve the model training effect, the training process can specifically include the following steps: 1. Set different parameters for multiple pre-built classification models to obtain multiple models to be trained; 2. According to the changes in the qualification level of the first stage and the second stage, train each model to be trained respectively, and evaluate the prediction indicators of the trained models; 3. Determine the optimal model from the multiple trained models according to the prediction indicators as the qualification prediction model. The above method uses a grid search method to set n groups of different (super) parameters for n classification models (such as xgboost models), put the data into n classification models for training to obtain n different classification models, and finally the trained classification model predicts the test set. For the results predicted by the n xgboost models on the test set, calculate the evaluation indicators, such as AUC, KS, precision, recall rate, etc., and select the optimal model as the qualification prediction model.
[0059] S104: Receive the target customer's credit information data, call the qualification prediction model to predict the user's future qualifications, and obtain output results.
[0060] When a financial institution grants credit to a user, it loads a trained user qualification prediction model, receives the credit information data of the target customer, extracts qualification features after data preprocessing, and obtains the target customer's feature data, which may include the user's credit data, transaction records, social network and other multi-dimensional information, to ensure the integrity and accuracy of the extracted feature data, thereby ensuring that the model can accurately predict. The feature data extraction process can refer to the introduction of step S101, which will not be repeated here.
[0061] After obtaining the characteristic data of the target customer, the prepared characteristic data is input into the loaded model to predict the user's future qualifications. The model will automatically calculate and output a probability value between [0,1] based on the input characteristic data, that is, the output result, which represents the probability that the user's future qualifications will improve. The larger the value, the higher the probability that the user's future qualifications will improve, realizing the future qualification changes of users (such as mob3) in the credit granting stage.
[0062] Based on the above introduction, this embodiment proposes a method for predicting customer credit qualifications in the field of financial credit. The method dynamically collects credit information data such as user credit data, transaction records, social networks, etc., and performs first-stage and second-stage user qualification evaluations on the user after performing qualification feature extraction. The second stage is later than the first stage and later than the credit granting stage. The qualification prediction training of the model is performed based on the feature data and the qualification levels of the two different periods, thereby obtaining a qualification prediction model that can accurately predict the user's qualification changes in the future and effectively identify users whose qualifications have improved. Unlike other qualification prediction methods that only focus on current static data, this method pays more attention to the changes in the user's qualifications in the future, and can provide another dimension of evaluation standards, providing financial institutions with more scientific and accurate decision-making basis, thereby providing more flexible and personalized services for different customers, which can improve user experience and satisfaction; and it improves the risk control ability in the field of financial credit and reduces credit risk.
[0063] It should be noted that although the operations of the method of the present invention are described in a particular order in the drawings, this does not require or imply that the operations must be performed in this particular order or that all illustrated operations must be performed to achieve desired results.
[0064] Optionally, in one embodiment, before executing step S104 to call the qualification prediction model to predict the user's future qualifications, the qualification level of the target customer in the first stage can be further evaluated as the target first level; determine whether the target first level is optimal; if so, output the result that the target customer is currently the best qualified customer.
[0065] For users with the best credit tier, since they are already in the best tier and there is no possibility of upgrading, they do not need to enter step S104 to apply inference. However, users in other credit tiers need to enter step S104 to apply inference.
[0066] Accordingly, before training the classification model according to the changes in qualification levels between the first and second stages in step S103, the relevant user data that has the best qualifications in the first stage can be further eliminated. This is because the user data is already in the stratum with the best qualifications and there is no possibility of improvement. Therefore, it can be removed during data collection and not included in the training set.
[0067] In one embodiment, after the output result is obtained in step S104, it can be further identified whether the output result is that the qualifications have improved; if so, the target customer and related customer information are output. The identified user with improved qualifications and related information are output to the financial institution for subsequent risk control, credit limit adjustment and other operations.
[0068] If the qualifications have not improved (including qualifications remaining unchanged or deteriorating), this is not limited in this embodiment, and the results can be output directly, or relevant information that may affect the credit qualifications can be further output for financial institutions to make subsequent user qualification adjustments and analysis.
[0069] Further references Figure 3 , which shows an exemplary structural block diagram of a customer credit qualification prediction device according to an embodiment of the present application, Figure 4 The overall structure diagram of a customer credit qualification prediction device provided by an embodiment of the present application is shown.
[0070] Figure 3 It includes: a data processing unit 101, a feature evaluation unit 102, a classification training unit 103 and a qualification prediction unit 104. Figure 4 The functions of the data processing unit 101 and the feature evaluation unit 102 are integrated into one module, and the other units are individually set up with models, and the two can refer to each other.
[0071] The data processing unit 101 is used to collect credit information data of each customer, extract qualification features after data preprocessing, and obtain feature data;
[0072] The feature evaluation unit 102 is used to evaluate the user's qualifications in the first and second stages according to the feature data and the qualification classification standard to obtain the qualification level; wherein the second stage is later than the first stage and later than the credit granting stage;
[0073] A classification training unit 103, used to train a classification model according to the changes in the qualification levels in the first stage and the second stage, and generate a qualification prediction model;
[0074] The qualification prediction unit 104 is used to receive the credit information data of the target customer, call the qualification prediction model to predict the user's future qualifications, and obtain an output result.
[0075] It should be understood that the units or modules described in the device are the same as those in the reference Figure 1 The various steps in the described method correspond to each other. Therefore, the operations and features described above for the method are also applicable to the device and the units contained therein, and will not be repeated here. The device can be pre-implemented in a browser or other security application of an electronic device, or loaded into a browser or its security application of an electronic device by downloading or the like. The corresponding units in the device can cooperate with the units in the electronic device to implement the solution of the embodiment of the present application.
[0076] For the several modules or units mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.
[0077] It should be noted that for details not disclosed in the customer credit qualification prediction device in the embodiment of the present application, please refer to the details disclosed in the above embodiments of the present application, which will not be repeated here.
[0078] Reference below Figure 5 , Figure 5 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.
[0079] like Figure 5 As shown, the computer system includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 508 to the random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation instructions of the system are also stored. The CPU 501, the ROM 502 and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.
[0080] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.
[0081] In particular, according to an embodiment of the present application, the above reference flow chart Figure 1The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present application are executed.
[0082] It should be noted that the computer-readable medium shown in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium such as a computer-readable storage medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
[0083] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operating instructions of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the aforementioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, the boxes represented by two connections can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operating instruction, or can be implemented with a combination of dedicated hardware and computer instructions.
[0084] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be arranged in a processor. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves.
[0085] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the above programs are used by one or more processors to execute the customer credit qualification prediction method described in the present application.
[0086] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.
Claims
1. A method for predicting customer credit qualifications, characterized in that: include: Collect credit information data of each customer, extract qualification features after data preprocessing, and obtain feature data; According to the characteristic data, the user's qualifications are evaluated in the first and second stages according to the qualification classification standard to obtain the qualification level; wherein the second stage is later than the first stage and later than the credit granting stage; Training a classification model based on the changes in qualification levels in the first stage and the second stage to generate a qualification prediction model; Receive the target customer's credit information data, call the qualification prediction model to predict the user's future qualifications, and obtain an output result.
2. The method according to claim 1, characterized in that Before calling the qualification prediction model to predict the user's future qualifications, the method further includes: Assess the qualification level of the target customer in the first stage as the target first level; Determining whether the target first level is optimal; If so, output the result that the target customer is currently the best qualified customer.
3. The method according to claim 1, characterized in that The credit information data includes at least two of: personal information, income data, asset data, credit data, transaction records, and social network information.
4. The method according to claim 1, characterized in that The second stage is the third month after the loan is disbursed.
5. The method according to claim 1, characterized in that The training of the classification model according to the change of the qualification level in the first stage and the second stage includes: Set different parameters for multiple pre-built classification models to obtain multiple models to be trained; According to the change of qualification level in the first stage and the second stage, each of the models to be trained is trained respectively, and the prediction index of the trained models is evaluated; According to the prediction index, an optimal model is determined from multiple trained models as a qualification prediction model.
6. The method according to claim 1, characterized in that After obtaining the output result, the method further includes: Identify whether the output result is that the qualification has improved; If so, the target customer and related customer information are output.
7. A device for predicting customer credit qualifications, characterized in that: include: The data processing unit is used to collect credit information data of each customer, extract qualification features after data preprocessing, and obtain feature data; A feature evaluation unit, configured to perform a first-stage and a second-stage user qualification evaluation on the user according to the feature data and by using a qualification classification standard to obtain a qualification level; wherein the second stage is later than the first stage and later than the credit granting stage; A classification training unit, used to train a classification model according to the changes in the qualification levels in the first stage and the second stage, and generate a qualification prediction model; The qualification prediction unit is used to receive the credit information data of the target customer, call the qualification prediction model to predict the user's future qualifications, and obtain an output result.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.