Commercial vehicle financing lease service overdue prediction method, device, equipment and medium

Abstract

The invention relates to the technical field of commercial vehicle leasing, and discloses a commercial vehicle financing leasing business overdue prediction method and device, equipment and a medium. The method comprises the following steps: acquiring vehicle basic data, vehicle operation data, vehicle locking data, tenant basic data and tenant loan data of a plurality of commercial vehicles; determining the objective repayment ability and subjective repayment willingness of the tenant through various data of the commercial vehicle; the objective repayment capability and subjective repayment willingness of a plurality of commercial vehicle tenants are utilized to establish a commercial vehicle financing lease service overdue prediction model, so that the overdue condition of the commercial vehicle is predicted before the repayment day of the commercial vehicle through the commercial vehicle financing lease service overdue prediction model, and therefore, the overdue condition of the commercial vehicle is predicted before the overdue condition actually occurs. Clients that may occur overdue are identified in advance.

Description

Technical Field

[0001] The present invention relates to the technical field of commercial vehicle leasing, and in particular to a method, device, equipment and medium for predicting overdue payments of commercial vehicle financial leasing business. Background Art

[0002] With the continuous development of commercial vehicle financial leasing business, financial leasing companies have attracted many lessees to purchase vehicles through financial leasing solutions through the flexible evolution of low down payment and low interest financial products. After the vehicle is sold, if the lessee fails to fulfill the contract and repay the loan in time, it will directly affect the security and control of the assets and funds of the financial leasing company, and have a serious impact on the sustainable development of the financial leasing business.

[0003] At present, financing companies mostly adopt post-overdue management, that is, when the lessee fails to repay the loan in time (that is, after the actual overdue), conventional collection methods such as litigation and vehicle repossession are adopted. However, such methods are inherently lagging and inefficient and costly, which is not conducive to the centralized and efficient management of financial leasing assets, and cannot effectively promote the promotion of differentiated financial leasing financial products for different customer groups and the implementation of a tiered risk control management model. Summary of the invention

[0004] The purpose of the present invention is to provide a method, device, equipment and medium for predicting overdue payments in commercial vehicle financial leasing business, which can pre-identify customers who may be overdue before the overdue payments actually occur.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a method for predicting overdue payments of commercial vehicle financial leasing business, comprising the following steps: Obtain vehicle basic data, vehicle operation data, vehicle lock data, lessee basic data, and lessee loan data of several commercial vehicles; Determine the overdue status of commercial vehicles based on vehicle lock data, and determine the lessee's objective repayment ability based on the non-overdue account period of commercial vehicles in the overdue status and the vehicle operation data of commercial vehicles of the same industry, model and region leased by the lessee; Determine the overdue rate of commercial vehicles based on the overdue status of commercial vehicles, and determine the credit status of the lessee based on the lessee's loan data, so as to determine the lessee's subjective willingness to repay by combining the overdue rate of commercial vehicles and the credit status of the lessee; By using the objective repayment ability and subjective repayment willingness of several commercial vehicle lessees, an overdue prediction model for commercial vehicle financial leasing business is established. Through the overdue prediction model for commercial vehicle financial leasing business, the overdue situation of commercial vehicles can be predicted before the repayment date of the commercial vehicles.

[0006] Optionally, the lessee's objective repayment ability and the determination of the lessee's subjective repayment willingness include: The initial sample data includes vehicle basic data, vehicle operation data, vehicle locking data, lessee basic data and lessee loan data; For the first sample data that meets the conditions of independence, normality and homogeneity of variance in the initial sample data, the variance analysis method ANOVA is used for screening to screen out the first sample data whose difference degree is greater than the first preset threshold value; For the second sample data that does not meet the independence, normality and variance homogeneity conditions and does not meet the linearity conditions in the initial sample data, the Spearman correlation coefficient is used for screening to screen out the second sample data whose Spearman correlation coefficient is greater than the second preset threshold; For the third sample data in the initial sample data that cannot be measured by numbers, the information entropy method is used for screening to screen out the third sample data whose information entropy change degree is greater than the third preset threshold value; By screening out the first sample data, the second sample data and the third sample data, the objective repayment ability and subjective repayment willingness of the lessee are obtained.

[0007] Optionally, the overdue prediction model for commercial vehicle financial leasing business is used to predict the overdue situation of the commercial vehicle before the repayment date of the commercial vehicle, including: Through the overdue prediction model of commercial vehicle financial leasing business, the probability of overdue payment of the commercial vehicle is predicted before the repayment date of the commercial vehicle, so as to determine whether the commercial vehicle will be overdue based on the probability of overdue payment of the commercial vehicle.

[0008] Optionally, the establishment of a commercial vehicle financing leasing business overdue prediction model includes: Obtain the predicted overdue situation and actual overdue situation of several commercial vehicles respectively, obtained through the overdue prediction model of commercial vehicle financial leasing business; According to the predicted overdue situation and actual overdue situation of several commercial vehicles, the recognition rate, misjudgment rate and accuracy rate of the overdue prediction model of commercial vehicle financial leasing business are obtained; among which, the recognition rate is the probability that the actual overdue result and the predicted overdue result are both overdue, the misjudgment rate is the probability that the actual overdue result is not overdue and the predicted overdue result is overdue, and the accuracy rate is the probability that the actual overdue result and the predicted overdue result are both overdue and the actual overdue result and the predicted overdue result are both not overdue; Based on the confusion matrix, the recognition rate, misjudgment rate and accuracy of the overdue prediction model of commercial vehicle financial leasing business are used to optimize the overdue prediction model of commercial vehicle financial leasing business.

[0009] Optionally, the basic vehicle data includes: vehicle identification code vin, organization, financing business start time, vehicle application type and landing access information; Vehicle operation data includes: mileage, fuel consumption, engine running time, attendance rate, empty driving rate, resident area, frequently traveled routes, transport distance and market segment; Vehicle lock data includes: vehicle vin, lock time, whether the vehicle is locked, and lock rate; Tenant basic data includes: customer due diligence and scoring data, credit report, age, marital status, household registration, education, average monthly income, occupation, real estate information, joint debt information, litigation information and guarantor information; Lessee loan data includes: loan amount, loan interest rate, loan term, remaining term, repayment date and account date.

[0010] An embodiment of the present invention further provides a commercial vehicle financial leasing business overdue prediction device, comprising: A data acquisition module is used to acquire basic vehicle data, vehicle operation data, vehicle lock data, lessee basic data, and lessee loan data of several commercial vehicles; The feature extraction module is used to determine the overdue status of commercial vehicles based on vehicle lock data, and determine the lessee's objective repayment ability based on the non-overdue account period of commercial vehicles in the overdue status and the vehicle operation data of commercial vehicles of the same industry, model and region leased by the lessee; Determine the overdue rate of commercial vehicles based on the overdue status of commercial vehicles, and determine the credit status of the lessee based on the lessee's loan data, so as to determine the lessee's subjective willingness to repay by combining the overdue rate of commercial vehicles and the credit status of the lessee; The overdue prediction module is used to predict the overdue situation of the commercial vehicle financing leasing business before the repayment date of the commercial vehicle through the overdue prediction model of the commercial vehicle financing leasing business.

[0011] An embodiment of the present invention also provides a computer device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned commercial vehicle financial leasing business overdue prediction method.

[0012] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned commercial vehicle financial leasing business overdue prediction method.

[0013] The commercial vehicle financing lease business overdue prediction method provided by the present invention has at least the following beneficial effects: First, the objective repayment ability and subjective repayment willingness of each commercial vehicle lessee are determined through various information of several commercial vehicles, such as vehicle basic data, vehicle operation data, vehicle locking data, lessee basic data and lessee loan data, and the characteristic portrait of the lessee is portrayed with numbers. Then, based on the objective repayment ability and subjective repayment willingness of several commercial vehicle lessees, an overdue prediction model for commercial vehicle financial leasing business is established. The overdue prediction model for commercial vehicle financial leasing business can be used to predict the overdue situation of commercial vehicle financial leasing business from the two dimensions of objective repayment ability and subjective repayment willingness of commercial vehicle lessees before the repayment date of the commercial vehicle, so as to facilitate financial leasing companies to take risk control measures in advance, reduce asset risks and improve business management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] One or more embodiments are exemplarily described by the pictures in the corresponding drawings, and these exemplary descriptions do not constitute limitations on the embodiments.

[0015] Figure 1 is a flowchart of a commercial vehicle financial leasing business overdue prediction method provided according to an embodiment of the present invention; Figure 2 A method for predicting overdue payments for commercial vehicle financing lease business according to an embodiment of the present invention is provided. Figure 1 ; Figure 3 A method for predicting overdue payments for commercial vehicle financing lease business according to an embodiment of the present invention is provided. Figure 2 ; Figure 4 It is a schematic diagram of a model tuning provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the embodiments of the present invention, many technical details are proposed in order to enable the reader to better understand the present invention. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present invention can be implemented. The division of the following embodiments is for the convenience of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined and referenced with each other without contradiction.

[0017] An embodiment of the present invention relates to a method for predicting overdue payments for commercial vehicle financial leasing business. The implementation details of the method for predicting overdue payments for commercial vehicle financial leasing business of this embodiment are described in detail below. The following content is only the implementation details provided for the convenience of understanding and is not necessary for implementing this solution.

[0018] The specific process of the overdue prediction method for commercial vehicle financial leasing business in this embodiment can be found in Figures 1 to 3 ,include: Step 101, obtaining vehicle basic data, vehicle operation data, vehicle locking data, lessee basic data and lessee loan data of several commercial vehicles.

[0019] Specifically, a number of commercial vehicles are randomly selected, and their basic vehicle data, vehicle operation data, vehicle locking data, lessee basic data and lessee loan data are collected to complete data preparation.

[0020] Among them, the basic vehicle data includes: vehicle identification code vin, organization, financing business start time, vehicle application type and landing access information, etc., to establish static basic vehicle information. Vehicle operation data includes: mileage, fuel consumption, engine running time, attendance rate (measurement of start of work), empty driving rate (measurement of whether goods are transported), permanent area, common running route, transportation distance and market segment (coal transportation, daily necessities transportation, etc.), etc., which are used to measure the basic situation of a certain vehicle type of the lessee in a certain operation area, and to establish dynamic measurement indicators. Vehicle locking data includes: vehicle vin, locking time, whether the vehicle is locked and locking rate, and the basic characteristics of remote locking after the user characterizes the vehicle history overdue. Lessee basic data includes: customer due diligence and scoring data, credit report, age, marital status, household registration, education, average monthly income, occupation, real estate information, joint debt information, litigation information and guarantor information, etc., which are used to evaluate the credit of the lessee, changes in relationship network, etc., and measure changes in the credit of natural persons. The lessee's loan data includes: loan amount, loan interest rate, loan term, remaining term, repayment date and account date, etc. A financial product matrix library is established for dynamic promotion, reserve and analysis of user-customized financial leasing products.

[0021] In one example, after obtaining the above data, the following data processing is performed: (1) For vehicle locking data, in practice, a vehicle may have multiple locking records in a month. To facilitate calculation, the data is aggregated into only one locking record per vehicle per month. Based on the locking data, an overdue identification rule is established, and the locking data is processed into: vehicle vin, account period month, and overdue identification.

[0022] (2) Summarize vehicle operation data and vehicle lock data by account period month.

[0023] (3) Integrate various data into: vehicle VIN, organization, financing business start time, vehicle application type, market segment, loan amount, loan term, remaining term, account period month, mileage, fuel consumption, engine running time, start-up rate, attendance rate, empty driving rate, permanent area, frequently traveled route, transportation distance, and whether it is overdue.

[0024] (4) Clean the data and remove abnormal data. For example, you can check the distribution of the values ​​of each data type and remove outliers.

[0025] In one example, the data characteristics (data type, data distribution) of various data are analyzed, and the appropriate feature screening method (ANOVA, Spearman, information entropy) is selected to screen the data with a high correlation with overdue behavior (yes, no) or overdue rate (overdue month / statistical month).

[0026] Specifically, the vehicle basic data, vehicle operation data, vehicle locking data, lessee basic data and lessee loan data are used as the initial sample data; for the first sample data that meets the conditions of independence, normality and homogeneity of variance in the initial sample data, the variance analysis method ANOVA is used for screening to screen out the first sample data whose difference degree is greater than the first preset threshold; for the second sample data that does not meet the conditions of independence, normality and homogeneity of variance and does not meet the linear condition in the initial sample data, the Spearman correlation coefficient is used for screening to screen out the second sample data whose Spearman correlation coefficient is greater than the second preset threshold; For the third sample data in the initial sample data that cannot be measured by numbers, information entropy is used for screening to screen out the third sample data whose degree of information entropy change is greater than a third preset threshold.

[0027] Among them, the ANOVA method is mainly based on the indicators shown in Table 1 for calculation: Table 1

[0028] In the table, k: the total number of factors; n: the number of observations; SSA: the sum of squares between groups; MSA: the mean square between groups; SSE: the sum of squares within groups; SST: the total sum of squares, decomposed into SSA (between groups) and SSE (within groups), that is, SST=SSA+SSE; MSE: the mean square within groups.

[0029] The Spearman correlation coefficient is calculated by the following formula: ; Where n is the number of observations; R(x) and R(y) are the ranks of x and y; R(x i ) and R(y i) are the positions of the i-th observation values ​​in variables x and y, that is, the ranking position corresponding to each observation value after the observation values ​​of variables x and y are sorted respectively; and : The average rank of x and y.

[0030] The information entropy method is calculated by the following formula: ; In the formula, p ( x i ) indicates a random event i The probability of occurrence; n: the number of observations.

[0031] Step 102, determine the overdue situation of the commercial vehicle based on the vehicle locking data, and determine the lessee's objective repayment ability based on the non-overdue account period months of the commercial vehicle in the overdue situation and the vehicle operation data of commercial vehicles of the same industry, same model and same region leased by the lessee.

[0032] Step 103, determining the overdue rate of the commercial vehicle according to the overdue situation of the commercial vehicle, and determining the credit status of the lessee according to the lessee's loan data, so as to determine the lessee's subjective willingness to repay by combining the overdue rate of the commercial vehicle and the credit status of the lessee.

[0033] In a specific implementation, the objective repayment ability and subjective repayment willingness of the lessee are obtained through the above-screened first sample data, second sample data and third sample data.

[0034] First, based on vehicle operation data, a repayment capacity warning mechanism is established to dynamically measure the objective repayment capacity of the vehicle. The repayment capacity of the vehicle in the current account period is determined based on the historical non-overdue account period months, the commercial vehicle benchmarks (mileage, attendance rate, operating rate, fuel consumption, etc.) of the same industry, the same model, and the same region. If it is higher than the average, the repayment capacity is positive, and if it is lower than the average, the repayment capacity is negative. That is, thresholds are set from two dimensions: horizontal (same industry, same model, same region) and vertical (own historical level) to evaluate the repayment capacity of the vehicle in the current account period month. Among them, the commercial vehicle benchmark refers to the average value of mileage, attendance rate, operating rate, fuel consumption and other data of the same industry, the same model, and the same region, and the own historical level refers to the average value of the single vehicle's historical non-overdue account period months.

[0035] Then, the subjective repayment enthusiasm (i.e., subjective repayment willingness) of the vehicle is characterized by the historical overdue records of the vehicle, and the historical overdue records are divided into different levels according to the overdue rate: 0≤overdue rate<0.2, repayment enthusiasm is very high; 0.2≤overdue rate<0.5, repayment enthusiasm is average; overdue rate>0.5, repayment enthusiasm is poor. The basic information of the lessee is further introduced, and the user credit rating is established by analyzing the overall credit behavior of the lessee, which serves as the dynamic input of the lessee's subjective repayment enthusiasm.

[0036] Step 104, using the objective repayment ability and subjective repayment willingness of several commercial vehicle lessees, establish a commercial vehicle financial leasing business overdue prediction model, so as to predict the overdue situation of the commercial vehicle before the repayment date of the commercial vehicle through the commercial vehicle financial leasing business overdue prediction model.

[0037] Specifically, through the overdue prediction model of commercial vehicle financial leasing business, before the repayment date of the commercial vehicle, the probability of overdue payment of the commercial vehicle is predicted, so as to determine whether the commercial vehicle will be overdue based on the probability of overdue payment of the commercial vehicle.

[0038] In an example, when establishing an overdue prediction model for commercial vehicle financial leasing business, the predicted overdue situations and actual overdue situations obtained by the commercial vehicle financial leasing business overdue prediction model for several commercial vehicles can be obtained respectively; according to the predicted overdue situations and actual overdue situations of several commercial vehicles, the recognition rate, error rate and accuracy rate of the overdue prediction model for commercial vehicle financial leasing business are obtained; among which, the recognition rate is the probability that the actual overdue result and the predicted overdue result are both overdue, the error rate is the probability that the actual overdue result is not overdue and the predicted overdue result is overdue, and the accuracy rate is the probability that the actual overdue result and the predicted overdue result are both overdue and the actual overdue result and the predicted overdue result are both not overdue; based on the confusion matrix, the recognition rate, error rate and accuracy rate of the overdue prediction model for commercial vehicle financial leasing business are used to optimize the overdue prediction model for commercial vehicle financial leasing business.

[0039] As shown in Table 2 and Figure 4 As shown in the figure, based on the confusion matrix, the recognition rate, misjudgment rate, and accuracy rate are introduced to optimize the above mechanism. Under the premise of ensuring the accuracy rate, the recognition rate is improved and the misjudgment rate is reduced: Table 2

[0040] Recognition rate: A / (A+C), i.e., vehicles predicted to be overdue among actual overdue vehicles; Misjudgment rate: B / (B+D), i.e., vehicles predicted to be overdue among vehicles that are not overdue; Accuracy: (A+D) / (A+B+C+D).

[0041] Considering the characteristics of the auto loan business, it is necessary to avoid economic losses caused by the lessee's failure to repay the loan due to the model's failure to identify the vehicle. Therefore, the model's recognition rate for overdue vehicles, that is, the model's "recall rate", will be appropriately improved, and a small number of non-overdue vehicles will be misjudged. This mainly includes: based on a large amount of historical actual overdue work order data, the mileage changes of overdue vehicles and non-overdue vehicles are analyzed by descriptive statistics, and the following three types of conditions are explored and formulated to screen overdue vehicles: Condition 1: The monthly mileage of the vehicle is lower than the average monthly mileage of non-overdue vehicles in the same period of the past two years; Condition 2: The monthly mileage of the vehicle is lower than the average monthly mileage of non-overdue vehicles; Condition 3: The vehicle has no mileage reported. As long as one of the above conditions is met, an early warning is triggered, and the model recognition rate reaches more than 80%, but the misjudgment rate is high and needs to be further adjusted. By continuously reducing the misjudgment rate and adjusting the condition parameters, the following rules are finally formulated: (1) Monthly mileage of non-overdue vehicles before: 50% or more of distance condition 1; 50% or more of distance condition 2. If any of the above conditions is met, an early warning will be triggered; (2) If a vehicle has been overdue before, an early warning will be triggered if the vehicle's monthly mileage conditions 1 and 2 are met; (3) If there is no mileage report, an early warning will be issued. The recognition rate has dropped by less than 10% compared with before the adjustment, and the misjudgment rate has dropped by about 30%, which initially meets business needs and determines the overdue early warning model.

[0042] It can be seen that this embodiment personalizes the early warning mechanism from two aspects: the objective repayment ability and subjective repayment enthusiasm of the vehicle, and predicts the vehicle's overdue behavior before the repayment date, for example, 5 days before the repayment date.

[0043] In the specific implementation, the overdue situation of commercial vehicle financial leasing business is predicted, and a vehicle overdue risk list can be obtained, which is convenient for financial leasing companies to take corresponding risk control measures for the batch of vehicles in advance and preserve the integrity of leased assets in time; district and county risk lists can also be obtained, which can provide data-based references for financial leasing companies in business development and resource allocation. In the due diligence stage at the beginning of business development, such business risks can be appropriately avoided. Based on this, customized financial products: According to the customer's objective repayment ability and subjective repayment enthusiasm, customers are divided into three categories: Category A (never overdue), Category B (occasional overdue), and Category C (high overdue). When customers repurchase or carry out other financial business, differentiated financial products can be recommended to each customer. Differentiated risk control strategies: Combined with user classification, in order to continuously improve the quality and efficiency of risk control management, differentiated risk control collection strategies can be implemented for customers, as shown in Table 3: Table 3

[0044] In this embodiment, firstly, the objective repayment ability and subjective repayment willingness of each commercial vehicle lessee are determined through various information of several commercial vehicles, such as vehicle basic data, vehicle operation data, vehicle locking data, lessee basic data and lessee loan data, so as to digitally characterize the characteristic portrait of the lessee. Then, based on the objective repayment ability and subjective repayment willingness of several commercial vehicle lessees, an overdue prediction model for commercial vehicle financial leasing business is established. Then, the overdue prediction model for commercial vehicle financial leasing business can be used to predict the overdue situation of commercial vehicle financial leasing business from the two dimensions of objective repayment ability and subjective repayment willingness of commercial vehicle lessees before the repayment date of the commercial vehicle, so as to facilitate financial leasing companies to take risk control measures in advance, reduce asset risks and improve business management efficiency.

[0045] The step division of the various methods above is only for clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the protection scope of the present invention. Adding insignificant modifications or introducing insignificant designs to the algorithm or process without changing the core design of the algorithm and process are all within the protection scope of the invention.

[0046] Another embodiment of the present invention relates to a commercial vehicle financing lease business overdue prediction device. The implementation details of the commercial vehicle financing lease business overdue prediction device of this embodiment are specifically described below. The following content is only for the convenience of understanding the implementation details provided, and is not necessary for the implementation of this solution. The commercial vehicle financing lease business overdue prediction device of this embodiment includes: A data acquisition module is used to acquire basic vehicle data, vehicle operation data, vehicle lock data, lessee basic data, and lessee loan data of several commercial vehicles; The feature extraction module is used to determine the overdue status of commercial vehicles based on vehicle lock data, and determine the lessee's objective repayment ability based on the non-overdue account period of commercial vehicles in the overdue status and the vehicle operation data of commercial vehicles of the same industry, model and region leased by the lessee; Determine the overdue rate of commercial vehicles based on the overdue status of commercial vehicles, and determine the credit status of the lessee based on the lessee's loan data, so as to determine the lessee's subjective willingness to repay by combining the overdue rate of commercial vehicles and the credit status of the lessee; The overdue prediction module is used to predict the overdue situation of the commercial vehicle financing leasing business before the repayment date of the commercial vehicle through the overdue prediction model of the commercial vehicle financing leasing business.

[0047] It is not difficult to find that this embodiment is a device embodiment corresponding to the above method embodiment, and this embodiment can be implemented in conjunction with the above method embodiment. The relevant technical details and technical effects mentioned in the above embodiment are still valid in this embodiment, and in order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the above embodiment.

[0048] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other units in this embodiment.

[0049] Another embodiment of the present invention relates to a computer device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the commercial vehicle financial leasing business overdue prediction method in the above-mentioned embodiments.

[0050] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0051] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0052] Another embodiment of the present invention relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0053] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as: ROM), random access memory (Random Access Memory, referred to as: RAM), disk or optical disk and other media that can store program codes.

[0054] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present invention, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present invention.

Claims

1. A method for predicting overdue payments in commercial vehicle financing leasing business, characterized in that: include: Obtain vehicle basic data, vehicle operation data, vehicle lock data, lessee basic data, and lessee loan data of several commercial vehicles; Determine the overdue status of commercial vehicles based on vehicle lock data, and determine the lessee's objective repayment ability based on the non-overdue account period of commercial vehicles in the overdue status and the vehicle operation data of commercial vehicles of the same industry, model and region leased by the lessee; Determine the overdue rate of commercial vehicles based on the overdue status of commercial vehicles, and determine the credit status of the lessee based on the lessee's loan data, so as to determine the lessee's subjective willingness to repay by combining the overdue rate of commercial vehicles and the credit status of the lessee; By using the objective repayment ability and subjective repayment willingness of several commercial vehicle lessees, an overdue prediction model for commercial vehicle financial leasing business is established. Through the overdue prediction model for commercial vehicle financial leasing business, the overdue situation of commercial vehicles can be predicted before the repayment date of the commercial vehicles.

2. The overdue prediction method for commercial vehicle financing leasing business according to claim 1 is characterized in that: The lessee's objective repayment ability and the lessee's subjective repayment willingness include: The initial sample data includes vehicle basic data, vehicle operation data, vehicle locking data, lessee basic data and lessee loan data; For the first sample data that meets the conditions of independence, normality and homogeneity of variance in the initial sample data, the variance analysis method ANOVA is used for screening to screen out the first sample data whose difference degree is greater than the first preset threshold value; For the second sample data that does not meet the independence, normality and variance homogeneity conditions and does not meet the linearity conditions in the initial sample data, the Spearman correlation coefficient is used for screening to screen out the second sample data whose Spearman correlation coefficient is greater than the second preset threshold; For the third sample data in the initial sample data that cannot be measured by numbers, the information entropy method is used for screening to screen out the third sample data whose information entropy change degree is greater than the third preset threshold value; By screening out the first sample data, the second sample data and the third sample data, the objective repayment ability and subjective repayment willingness of the lessee are obtained.

3. The overdue prediction method for commercial vehicle financing leasing business according to claim 1 is characterized in that: The overdue prediction model for commercial vehicle financing leasing business is used to predict the overdue situation of commercial vehicles before the repayment date of the commercial vehicles, including: Through the overdue prediction model of commercial vehicle financial leasing business, the probability of overdue payment of the commercial vehicle is predicted before the repayment date of the commercial vehicle, so as to determine whether the commercial vehicle will be overdue based on the probability of overdue payment of the commercial vehicle.

4. The overdue prediction method for commercial vehicle financing leasing business according to claim 1 is characterized in that: The establishment of the overdue prediction model for commercial vehicle financing leasing business includes: Obtain the predicted overdue situation and actual overdue situation of several commercial vehicles respectively, obtained through the overdue prediction model of commercial vehicle financial leasing business; According to the predicted overdue situation and actual overdue situation of several commercial vehicles, the recognition rate, misjudgment rate and accuracy rate of the overdue prediction model of commercial vehicle financial leasing business are obtained; among which, the recognition rate is the probability that the actual overdue result and the predicted overdue result are both overdue, the misjudgment rate is the probability that the actual overdue result is not overdue and the predicted overdue result is overdue, and the accuracy rate is the probability that the actual overdue result and the predicted overdue result are both overdue and the actual overdue result and the predicted overdue result are both not overdue; Based on the confusion matrix, the recognition rate, misjudgment rate and accuracy of the overdue prediction model of commercial vehicle financial leasing business are used to optimize the overdue prediction model of commercial vehicle financial leasing business.

5. The overdue prediction method for commercial vehicle financing leasing business according to any one of claims 1 to 4, characterized in that: The basic vehicle data includes: vehicle identification code vin, organization, financing business start time, vehicle application type and landing access information; Vehicle operation data includes: mileage, fuel consumption, engine running time, attendance rate, empty driving rate, resident area, frequently traveled routes, transport distance and market segment; Vehicle lock data includes: vehicle vin, lock time, whether the vehicle is locked, and lock rate; Tenant basic data includes: customer due diligence and scoring data, credit report, age, marital status, household registration, education, average monthly income, occupation, real estate information, joint debt information, litigation information and guarantor information; Lessee loan data includes: loan amount, loan interest rate, loan term, remaining term, repayment date and account date.

6. A commercial vehicle financing lease business overdue prediction device, characterized in that: include: A data acquisition module is used to acquire basic vehicle data, vehicle operation data, vehicle lock data, lessee basic data, and lessee loan data of several commercial vehicles; The feature extraction module is used to determine the overdue status of commercial vehicles based on vehicle lock data, and determine the lessee's objective repayment ability based on the non-overdue account period of commercial vehicles in the overdue status and the vehicle operation data of commercial vehicles of the same industry, model and region leased by the lessee; Determine the overdue rate of commercial vehicles based on the overdue status of commercial vehicles, and determine the credit status of the lessee based on the lessee's loan data, so as to determine the lessee's subjective willingness to repay by combining the overdue rate of commercial vehicles and the credit status of the lessee; The overdue prediction module is used to predict the overdue situation of the commercial vehicle financing leasing business before the repayment date of the commercial vehicle through the overdue prediction model of the commercial vehicle financing leasing business.

7. A computer device, characterized in that: include: at least one processor; And, a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for overdue prediction of commercial vehicle financial leasing business as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for predicting overdue commercial vehicle financial leasing business according to any one of claims 1 to 5 is implemented.

Images