Resource target customer determination method, device and electronic equipment

Abstract

The present disclosure relates to a resource target customer determination method, device, electronic device and computer-readable medium. The method comprises: determining the risk scores of multiple customers based on the resource information and risk scoring model of the multiple customers; extracting at least one customer whose risk score is greater than a threshold; determining the profit score of the at least one customer based on the resource information and profit scoring model of the at least one customer; and determining the target customer from the at least one customer based on the profit score. The resource target customer determination method, device, electronic device and computer-readable medium involved in the present disclosure can screen target users from multiple perspectives such as risk and profit, improve the pass rate of the overall resource service, and increase the company's profit.

Description

Technical Field

[0001] The present disclosure relates to the field of computer information processing, and in particular, to a resource target customer determination method, device, electronic device and computer-readable medium. Background Art

[0002] With the development of the economy, in order to meet the needs of their own development, individual users or corporate users often borrow money from resource service agencies. For resource service agencies, users' borrowing activities are likely to bring risks to resource service companies. Before the repayment period expires, major adverse changes in the financial and business conditions of the borrower (credit user) are likely to affect its ability to perform its obligations, thereby causing risks such as bad debts and bad debts. Therefore, in order to reduce the probability of such risks, resource service agencies need to conduct risk assessments on borrowers. Based on the results of the risk assessment, resource service companies can refuse to provide services to users with high resource risks and who cannot repay their loans.

[0003] At present, the identification of resource risk is often obtained by analyzing the credit risk of users. Credit risk, also known as counterparty risk or performance risk, refers to the risk that the counterparty will not fulfill its due debts. As the main risk faced by the Internet resource service industry, credit risk has always been the core content of credit risk management. However, in practice, it is found that although some customers cannot repay on time, due to resource benefits such as liquidated damages and interest, when these defaulting users repay, the profits they bring are higher than those of customers who repay on time. Moreover, among the customers who are rejected for loans after credit risk assessment, the profits brought by some customers can cover the risks and bring profit income to resource service companies. How to analyze such users and provide reasonable resource services to them is an urgent problem to be solved.

[0004] Therefore, a new resource target customer determination method, device, electronic device and computer-readable medium are needed.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] In view of this, the present disclosure provides a resource target customer determination method, device, electronic device and computer-readable medium, which can screen target users from multiple angles such as risk and profit, improve the overall resource service pass rate, and increase company profits.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to one aspect of the present disclosure, a method for determining resource target customers is proposed, the method comprising: determining risk scores of multiple customers based on resource information of the multiple customers and a risk scoring model; extracting at least one customer whose risk score is greater than a threshold; determining a profit score of the at least one customer based on the resource information of the at least one customer and a profit scoring model; and determining a target customer from the at least one customer based on the profit score.

[0009] Optionally, it also includes: training the first machine learning model through historical customer repayment information to generate the risk scoring model, and the risk scoring model is used to generate a risk score for customer default repayment.

[0010] Optionally, the first machine learning model is trained using historical customer repayment information, including: training a gradient boosting decision tree model using historical customer repayment information.

[0011] Optionally, it also includes: training a second machine learning model through historical customer revenue information to generate the profit scoring model, and the profit scoring model is used to generate a profit score for the annualized revenue brought by the customer.

[0012] Optionally, the second machine learning model is trained using historical customer revenue information, including: training a chi-square automatic interaction detection decision tree model using historical customer revenue information.

[0013] Optionally, extracting at least one customer whose risk score is greater than a threshold comprises: determining the threshold through historical experience data; and comparing the risk scores of the multiple customers with the threshold to extract the at least one customer.

[0014] Optionally, determining a target customer from the at least one customer based on the profit score includes: sorting the at least one customer according to its corresponding profit score; and determining the target customer from the at least one customer based on the sorting result and a preset condition.

[0015] Optionally, target customers are determined from the at least one customer based on the sorting result and preset conditions, including: determining the internal rate of return based on risk expenditure and cost expenditure; and based on the sorting result, customers from the at least one customer whose profit score is greater than the internal rate of return are selected in sequence as the target customers.

[0016] Optionally, the method further includes: extracting at least one customer whose risk score is less than or equal to a threshold, and determining the at least one customer as a target customer.

[0017] Optionally, the method further includes: determining a resource service strategy for the target customer based on the risk score and the profit score.

[0018] According to one aspect of the present disclosure, a resource target customer determination device is proposed, which includes: a risk module, used to determine the risk scores of multiple customers based on the resource information of the multiple customers and a risk scoring model; an extraction module, used to extract at least one customer whose risk score is greater than a threshold; a profit score, used to determine the profit score of the at least one customer based on the resource information of the at least one customer and the profit scoring model; and a target module, used to determine a target customer from the at least one customer based on the profit score.

[0019] Optionally, it also includes: a first training module, used to train the first machine learning model through historical customer repayment information to generate the risk scoring model, and the risk scoring model is used to generate a risk score for customer default repayment.

[0020] Optionally, the first training module is further used to train the gradient boosting decision tree model through historical customer repayment information.

[0021] Optionally, it also includes: a second training module, used to train the second machine learning model through historical customer revenue information to generate the profit scoring model, and the profit scoring model is used to generate a profit score for the annualized revenue brought by the customer.

[0022] Optionally, the second training module is further used to train the chi-square automatic interaction detection decision tree model through historical customer revenue information.

[0023] Optionally, the extraction module includes: a threshold unit, used to determine the threshold through historical experience data; and a comparison unit, used to compare the risk scores of the multiple customers with the threshold to extract the at least one customer.

[0024] Optionally, the target module includes: a sorting unit, used to sort the at least one customer according to its corresponding profit score; and a target unit, used to determine a target customer from the at least one customer based on the sorting result and preset conditions.

[0025] Optionally, the target unit is further used to determine the internal rate of return based on risk expenditure and cost expenditure; and based on the sorting result, the customers among the at least one customer whose profit score is greater than the internal rate of return are selected as the target customers in turn.

[0026] Optionally, it further includes: a customer module, used to extract at least one customer whose risk score is less than or equal to a threshold, and determine the at least one customer as a target customer.

[0027] Optionally, it further includes: a strategy module, used to determine a resource service strategy for the target customer based on the risk score and the profit score.

[0028] According to one aspect of the present disclosure, an electronic device is proposed, which includes: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0029] According to one aspect of the present disclosure, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the method described above is implemented.

[0030] According to the resource target customer determination method, device, electronic device and computer-readable medium disclosed in the present invention, the risk scores of multiple customers are determined based on the resource information of multiple customers and the risk scoring model; at least one customer whose risk score is greater than a threshold is extracted; the profit score of at least one customer is determined based on the resource information of the at least one customer and the profit scoring model; and the target customer is determined from the at least one customer based on the profit score. This method can screen target users from multiple angles such as risk and profit, thereby improving the pass rate of the overall resource service and increasing the company's profits.

[0031] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail its exemplary embodiments with reference to the accompanying drawings. The accompanying drawings described below are only some embodiments of the present disclosure, and it is clear to a person skilled in the art that other accompanying drawings can be obtained from these accompanying drawings without creative work.

[0033] Figure 1 The present invention is a system block diagram showing a method and device for determining a resource target client according to an exemplary embodiment.

[0034] Figure 2 The present invention is a flowchart of a method for determining a resource target client according to an exemplary embodiment.

[0035] Figure 3 The figure is a flow chart showing a method for determining a resource target client according to another exemplary embodiment.

[0036] Figure 4 The diagram is a schematic diagram of a method for determining a resource target client according to another exemplary embodiment.

[0037] Figure 5 The diagram is a schematic diagram of a method for determining a resource target client according to another exemplary embodiment.

[0038] Figure 6 The invention is a block diagram showing a device for determining a resource target client according to an exemplary embodiment.

[0039] Figure 7 It is a block diagram of a device for determining a resource target client according to another exemplary embodiment.

[0040] Figure 8 It is a block diagram of an electronic device according to an exemplary embodiment.

[0041] Fig. 9 It is a block diagram of a computer-readable medium according to an exemplary embodiment. DETAILED DESCRIPTION

[0042] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0043] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0044] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0045] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0046] It should be understood that although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the disclosed concepts. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more.

[0047] Those skilled in the art will appreciate that the drawings are merely schematic diagrams of example embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing the present disclosure, and therefore cannot be used to limit the protection scope of the present disclosure.

[0048] In customer risk management, the formulation of loan rejection and return rules generally only considers the risk perspective. In practice, it is found that the profits brought by some of the rejected loan customers can cover the risks and bring profit income to the company. The inventor of the present disclosure believes that the formulation of loan rejection rules should not only consider the risks, but also the profits brought by the customers. Therefore, the formulation of the strategy of whether to provide resource services to customers should also take the profits that customers can bring in the future as an important measurement indicator. The resource target customer determination method and device disclosed in the present disclosure are described in detail below in conjunction with specific embodiments.

[0049] Figure 1 The present invention is a system block diagram showing a method and device for determining a resource target client according to an exemplary embodiment.

[0050] like Figure 1 As shown, the system architecture 10 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0051] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as resource service applications, shopping applications, web browser applications, instant messaging tools, email clients, social platform software, etc.

[0052] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0053] The server 105 may be a server that provides various services, such as a background management server that provides support for resource service websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze the received user data and feed back the processing results (such as whether the user is the target user and whether to provide resource services for the user) to the administrator of the resource service website.

[0054] The server 105 may, for example, determine the risk scores of the multiple customers based on the resource information and risk scoring model of the multiple customers; the server 105 may, for example, extract at least one customer whose risk score is greater than a threshold; the server 105 may, for example, determine the profit score of the at least one customer based on the resource information and profit scoring model of the at least one customer; the server 105 may, for example, determine the target customer from the at least one customer based on the profit score.

[0055] The server 105 can also train the first machine learning model, for example, using historical customer repayment information to generate the risk scoring model, and the risk scoring model is used to generate a risk score for customer default repayment.

[0056] The server 105 may also train the second machine learning model, for example, using historical customer revenue information to generate the profit scoring model, where the profit scoring model is used to generate a profit score for the annualized revenue brought by the customer.

[0057] Server 105 can be a physical server, or can be composed of multiple servers, for example. A part of server 105 can be used to train the first machine learning model through historical customer repayment information to generate the risk scoring model, and the risk scoring model is used to generate a risk score for customer default repayment; a part of server 105 can be used to train the second machine learning model through historical customer income information to generate the profit scoring model, and the profit scoring model is used to generate a profit score for the annualized income brought by the customer; and a part of server 105 can also be used to determine target customers from the at least one customer based on the risk score and the profit score.

[0058] It should be noted that the resource target client determination method provided in the embodiment of the present disclosure can be executed by the server 105, and accordingly, the resource target client determination device can be set in the server 105. The web page provided to users for browsing the resource service platform is generally located in the terminal devices 101, 102, and 103.

[0059] Figure 2 The flowchart of a resource target client determination method according to an exemplary embodiment is shown. The resource target client determination method 20 at least includes steps S202 to S208.

[0060] like Figure 2 As shown, in S202, the risk scores of the multiple customers are determined based on the resource information of the multiple customers and the risk scoring model. The first machine learning model can be trained with the historical customer repayment information to generate the risk scoring model, which is used to generate the risk score of the customer default repayment.

[0061] In S204, at least one customer whose risk score is greater than a threshold is extracted, including: determining the threshold through historical experience data; and comparing the risk scores of the plurality of customers with the threshold to extract the at least one customer.

[0062] In S206, a profit score of the at least one customer is determined based on the resource information of the at least one customer and the profit score model. The profit score model can be generated by training the second machine learning model with historical customer revenue information, and the profit score model is used to generate a profit score of the annualized revenue brought by the customer.

[0063] Furthermore, the profit scoring model uses the actual IRR (internal rate of return) as an indicator to measure the future profits of customers, which is also the output data of the model. The actual IRR is a continuous variable that can not only provide more accurate information about borrowers, but also contain information about whether customers will default in the future. Selecting user-related resource information as input variables, using the profit scoring model, it is possible to score the input user and output the predicted IRR corresponding to the user.

[0064] In S208, a target customer is determined from the at least one customer based on the profit score, including: sorting the at least one customer according to its corresponding profit score; and determining the target customer from the at least one customer based on the sorting result and a preset condition.

[0065] In one embodiment, the method further includes: extracting at least one customer whose risk score is less than or equal to a threshold, and determining the at least one customer as a target customer.

[0066] In one embodiment, it further includes: determining a resource service strategy for the target customer based on the risk score and the profit score. The profit score model assists the risk score model to generate a loan rejection recovery strategy for customers who have been rejected for loans, so as to screen out customers who can receive resource services from customers who have been rejected for loans. This method can improve the transaction approval rate and the company's profitability.

[0067] In one embodiment, for example, the estimated annualized risk of customers rejected by the risk model is twice that of customers who pass normally. Assuming that the annualized risk of customers who pass normally is 6%, the annualized risk threshold of rejected customers can be 12%. Among these rejected customers, if the actual IRR of a customer is 33%, minus the annualized risk of 12% and the cost, these customers can still bring profits to the company's operations.

[0068] According to the resource target customer determination method disclosed in the present invention, the risk scores of multiple customers are determined based on their resource information and risk scoring models; at least one customer whose risk score is greater than a threshold is extracted; the profit score of at least one customer is determined based on the resource information and profit scoring model of the at least one customer; and the target customer is determined from the at least one customer based on the profit score. This method can screen target users from multiple angles such as risk and profit, thereby improving the pass rate of overall resource services and increasing company profits.

[0069] It should be clearly understood that the present disclosure describes how to form and use specific examples, but the principles of the present disclosure are not limited to any details of these examples. On the contrary, based on the teachings of the contents disclosed in the present disclosure, these principles can be applied to many other embodiments.

[0070] Figure 3 The figure is a flow chart showing a method for determining a resource target client according to another exemplary embodiment. Figure 3 The process shown is Figure 2 The process shown is a detailed description of S208 "determining a target customer from the at least one customer based on the profit score".

[0071] like Figure 3 As shown, in S302, the at least one customer is sorted according to its corresponding profit score.

[0072] In S304, the internal rate of return is determined based on the risk expenditure and the cost expenditure.

[0073] In S306, based on the ranking result, customers among the at least one customer whose profit score is greater than the internal rate of return are selected in turn as the target customers.

[0074] For the customer group that was rejected, the profit scoring model is used to estimate the actual IRR of this group of customers. The customers are sorted from large to small, and the top customers can be recovered. The recovery principle is that the actual IRR of the recovered customers can cover the risks and costs. For example, the actual IRR of the recovered group is 33%, minus the annualized risk of 12% and the costs. These customers can still bring profits to the company's operations.

[0075] Figure 4The diagram is a schematic diagram of a method for determining a resource target client according to another exemplary embodiment. Figure 4 It is a detailed description of "training a first machine learning model through historical customer repayment information to generate the risk scoring model, and the risk scoring model is used to generate a risk score for customer default repayment."

[0076] In one embodiment, the gradient boosting decision tree model may be trained, for example, using historical customer repayment information.

[0077] GBDT (Gradient Boosting Decision Tree) is an iterative decision tree algorithm, which consists of multiple decision trees, and the conclusions of all trees are accumulated as the final answer. In one embodiment, GBDT is an algorithm that classifies or regresses data by using an additive model (i.e., a linear combination of basis functions) to analyze and calculate the repayment information of historical customers, and continuously reduces the residuals generated by the training process. GBDT is looking for the optimal function F, and each time the loss function is partialed out to obtain a negative gradient, and the loss function is minimized by fitting this negative gradient. GBDT generates a weak classifier through multiple rounds of iterations, and each round of iteration generates a weak classifier. Each classifier is trained based on the residual of the previous round of classifiers. The weak classifier generally selects a CART tree, but the depth of each classification regression tree will not be very deep. The final risk score is obtained by weighted summing the results of the weak classifiers obtained from each round of training.

[0078] Figure 5 The diagram is a schematic diagram of a method for determining a resource target client according to another exemplary embodiment. Figure 5 It is a detailed description of "training the second machine learning model through historical customer revenue information to generate the profit scoring model, and the profit scoring model is used to generate a profit score for the annualized revenue brought by the customer."

[0079] In one embodiment, the chi-square automatic interaction detection decision tree model may be trained, for example, using historical customer revenue information.

[0080] The chi-squared automatic interaction detector (CHAID) is a tool used to discover the relationship between the basic information of historical customers and their corresponding income information. CHAID can be used for prediction and classification, and for detecting interactions between variables. In one embodiment, the sample is optimally segmented according to the income information of a given historical user and its corresponding basic information, and the multivariate contingency table is automatically judged and grouped according to the significance of the chi-square test to divide the historical users into different groups, each of which corresponds to a rate of return. The chi-squared automatic interaction detection method can be used to quickly and effectively mine the main influencing factors. It can not only handle nonlinear and highly correlated data, but also take missing values ​​into account, which can overcome the limitations of traditional parameter test methods in these aspects.

[0081] The classification process of the chi-square automatic interaction detection method is: first select the response variable for classification, then use the explanatory variable and the response variable for cross-classification to generate a series of two-dimensional classification tables, calculate the eigenvalues ​​of the two-dimensional classification tables respectively, and use the two-dimensional table with the smallest eigenvalue as the best initial classification table. On the basis of the best two-dimensional classification table, continue to use the explanatory variable to classify the response variable, and repeat the above process until the eigenvalue is greater than the set statistically significant threshold.

[0082] Those skilled in the art will appreciate that all or part of the steps for implementing the above embodiments are implemented as a computer program executed by a CPU. When the computer program is executed by the CPU, the above functions defined by the above method provided by the present disclosure are performed. The program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0083] In addition, it should be noted that the above figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0084] The following are embodiments of the device disclosed herein, which can be used to execute the method embodiments disclosed herein. For details not disclosed in the device embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0085] Figure 6 FIG. 1 is a block diagram of a resource target client determination device according to an exemplary embodiment. Figure 6 As shown, the resource target customer determination device 60 includes: a risk module 602 , an extraction module 604 , a profit module 606 , and a target module 608 .

[0086] The risk module 602 is used to determine the risk scores of the multiple customers based on the resource information of the multiple customers and the risk scoring model;

[0087] The extraction module 604 is used to extract at least one customer whose risk score is greater than a threshold; the extraction module 604 includes: a threshold unit, used to determine the threshold through historical experience data; and a comparison unit, used to compare the risk scores of the multiple customers with the threshold to extract the at least one customer.

[0088] The profit module 606 is used to determine the profit score of the at least one customer based on the resource information of the at least one customer and the profit score model; and

[0089] The target module 608 is used to determine the target customer from the at least one customer based on the profit score. The target module 608 includes: a sorting unit, used to sort the at least one customer according to its corresponding profit score; a target unit, used to determine the target customer from the at least one customer based on the sorting result and a preset condition. The target unit is also used to determine the internal rate of return based on the risk expenditure and the cost expenditure; and based on the sorting result, sequentially select the customers whose profit score is greater than the internal rate of return from the at least one customer as the target customers.

[0090] Figure 7 FIG. 1 is a block diagram of a resource target client determination device according to another exemplary embodiment. Figure 7 As shown, the resource target client determination device 70 includes: a first training module 702 , a second training module 704 , a client module 706 , and a strategy module 708 .

[0091] The first training module 702 is used to train the first machine learning model through historical customer repayment information to generate the risk scoring model, and the risk scoring model is used to generate a risk score for customer default repayment. The first training module 702 is also used to train the gradient boosting decision tree model through historical customer repayment information.

[0092] The second training module 704 is used to train the second machine learning model through the historical customer revenue information to generate the profit scoring model, and the profit scoring model is used to generate the profit score of the annualized revenue brought by the customer. The second training module 704 is also used to train the chi-square automatic interaction detection decision tree model through the historical customer revenue information.

[0093] The customer module 706 is used to extract at least one customer whose risk score is less than or equal to a threshold, and determine the at least one customer as a target customer.

[0094] The strategy module 708 is used to determine a resource service strategy for the target customer based on the risk score and the profit score.

[0095] According to the resource target customer determination device disclosed in the present invention, the risk scores of multiple customers are determined based on the resource information of multiple customers and the risk scoring model; at least one customer whose risk score is greater than a threshold is extracted; the profit score of at least one customer is determined based on the resource information of the at least one customer and the profit scoring model; and the target customer is determined from the at least one customer based on the profit score. This method can screen target users from multiple angles such as risk and profit, thereby improving the pass rate of the overall resource service and increasing the company's profits.

[0096] Figure 8 It is a block diagram of an electronic device according to an exemplary embodiment.

[0097] Refer to the following Figure 8 The electronic device 800 according to this embodiment of the present disclosure is described. Figure 8 The electronic device 800 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0098] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), a display unit 840, etc.

[0099] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 executes the steps according to various exemplary embodiments of the present disclosure described in the electronic prescription circulation processing method section of this specification. For example, the processing unit 810 can execute the following steps: Figure 2 , Figure 3 Follow the steps shown in .

[0100] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0101] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0102] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0103] The electronic device 800 may also communicate with one or more external devices 800' (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 800, and / or communicate with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 850. Furthermore, the electronic device 800 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 860. The network adapter 860 may communicate with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0104] Through the above description of the implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by combining software with necessary hardware. Fig. 9 As shown, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiment of the present disclosure.

[0105] The software product may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 thereof.

[0106] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0107] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0108] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by a device, the computer-readable medium implements the following functions: determining the risk scores of multiple customers based on the resource information of multiple customers and the risk scoring model; extracting at least one customer whose risk score is greater than a threshold; determining the profit score of at least one customer based on the resource information of the at least one customer and the profit scoring model; and determining a target customer from the at least one customer based on the profit score.

[0109] Those skilled in the art will appreciate that the above modules can be distributed in the device according to the description of the embodiment, or can be changed accordingly and only used in one or more devices different from the embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

[0110] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0111] The exemplary embodiments of the present disclosure are specifically shown and described above. It should be understood that the present disclosure is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present disclosure is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended claims.

Claims

1. A method for determining resource target customers, characterized in that: include: The gradient boosting decision tree model is trained through the repayment information of historical customers. The gradient boosting decision tree analyzes and calculates the repayment information of historical customers through the linear combination of basis functions, continuously reduces the residual generated in the training process to classify or regress the data, and then generates a risk scoring model. The risk scoring model generates a risk score for customer default repayment by weighted summing the results obtained in each round of training; The chi-square automatic interaction detection decision tree model is trained through the historical customer income information. The chi-square automatic interaction detection decision tree model optimally segments the sample according to the given historical user income information and its corresponding basic information, and automatically determines and groups the multivariate contingency table according to the significance of the chi-square test, thereby generating a profit scoring model. The profit scoring model automatically determines and groups the multivariate contingency table, and each group corresponds to a rate of return, thereby generating a profit score of the annualized income brought by the customer; Determining risk scores of the plurality of customers based on resource information of the plurality of customers and a risk scoring model; Extracting at least one customer whose risk score is greater than a threshold; determining a profit score of the at least one customer based on the resource information of the at least one customer and a profit score model; as well as sorting the at least one customer according to its corresponding profit score; Determine the internal rate of return based on risk expenditure and cost expenditure; Based on the ranking result, the customers whose profit scores are greater than the internal rate of return among the at least one customer are selected as target customers in turn; When the target customer is an invalid customer, recover the target customer; A resource service strategy is determined for the target customer based on the risk score and the profit score.

2. The method according to claim 1, characterized in that Extracting at least one customer whose risk score is greater than a threshold includes: Determine the threshold value through historical experience data; and The risk scores of the plurality of customers are compared with the threshold to extract the at least one customer.

3. A resource target customer determination device, characterized in that: include: The first training module is used to train the gradient boosting decision tree model through the historical customer repayment information. The gradient boosting decision tree analyzes and calculates the historical customer repayment information through the linear combination of basis functions, continuously reduces the residual generated in the training process to classify or regress the data, and then generates a risk scoring model. The risk scoring model generates a risk score for customer default repayment by weighted summing the results obtained in each round of training; The second training module is used to train the chi-square automatic interaction detection decision tree model through the historical customer income information. The chi-square automatic interaction detection decision tree model optimally divides the sample according to the given historical user income information and its corresponding basic information, and automatically determines and groups the multivariate contingency table according to the significance of the chi-square test, thereby generating a profit scoring model. The profit scoring model automatically determines and groups the multivariate contingency table, and each group corresponds to a rate of return, thereby generating a profit score of the annualized income brought by the customer; A risk module, configured to determine risk scores of the plurality of customers based on resource information of the plurality of customers and a risk scoring model; An extraction module, used for extracting at least one customer whose risk score is greater than a threshold; a profit module, configured to determine a profit score of the at least one customer based on the resource information of the at least one customer and a profit score model; as well as A target module, used for sorting the at least one customer according to its corresponding profit score; Determine the internal rate of return based on risk expenditure and cost expenditure; based on the sorting result, select the customers among the at least one customer whose profit score is greater than the internal rate of return as target customers in turn, and determine the resource service strategy for the target customers based on the risk score and the profit score.

4. The device according to claim 3, characterized in that The extraction module comprises: A threshold unit, used to determine the threshold through historical experience data; and A comparing unit is used to compare the risk scores of the multiple customers with the threshold to extract the at least one customer.

5. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-2.

6. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 2 is implemented.

Images