CN113592623A - Construction method of risk assessment system before vehicle loan and credit and risk assessment method - Google Patents
Construction method of risk assessment system before vehicle loan and credit and risk assessment method Download PDFInfo
- Publication number
- CN113592623A CN113592623A CN202110834150.2A CN202110834150A CN113592623A CN 113592623 A CN113592623 A CN 113592623A CN 202110834150 A CN202110834150 A CN 202110834150A CN 113592623 A CN113592623 A CN 113592623A
- Authority
- CN
- China
- Prior art keywords
- risk
- data
- credit
- car
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 96
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000010276 construction Methods 0.000 title claims abstract description 13
- 238000012216 screening Methods 0.000 claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims description 45
- 238000011156 evaluation Methods 0.000 claims description 32
- 238000003066 decision tree Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 238000007473 univariate analysis Methods 0.000 claims description 10
- 238000007621 cluster analysis Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 4
- 238000012550 audit Methods 0.000 description 3
- 238000003012 network analysis Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000001520 comb Anatomy 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a construction method, a risk assessment method, a device, equipment and a storage medium of a vehicle loan pre-loan risk assessment system, wherein the method comprises the following steps: constructing a vehicle credit risk dimension according to the data of the vehicle credit service dimensions and the vehicle credit risk event library; generating client sample data according to the data of the plurality of car loan service dimensions; screening target data items in the client sample data, and determining effective risk indexes corresponding to the car loan risk dimension according to the target data items; and constructing a vehicle loan pre-credit risk assessment system according to the effective risk indexes. The method can comprehensively and accurately evaluate the risk before the car loan.
Description
Technical Field
The application relates to the technical field of computers, in particular to a construction method, a risk evaluation method and device, computer equipment and a storage medium of a pre-vehicle loan risk evaluation system.
Background
When handling car loan business, business personnel need to submit personal information and property information of customers to a customer manager of a credit institution such as a bank to judge whether the loan of a certain car financial product can be passed after the information is collected. Due to the fact that business scenes related to car lending are complex, the traditional car lending pre-lending risk assessment mode only carries out pre-lending risk assessment through personal information and property information of customers, only partial pre-lending risks are considered, and car lending pre-lending risks cannot be assessed comprehensively and accurately.
Therefore, how to comprehensively and accurately evaluate the risk before car loan is a technical problem to be solved at present.
Disclosure of Invention
The present application mainly aims to provide a method for constructing a pre-loan risk assessment system, a risk assessment method, a risk assessment apparatus, a computer device, and a storage medium, so as to solve the above problems.
In order to achieve the above object, according to one aspect of the present application, there is provided a method for constructing a pre-car loan risk assessment system, including:
constructing a vehicle credit risk dimension according to the data of the vehicle credit service dimensions and the vehicle credit risk event library;
generating client sample data according to the data of the plurality of car loan service dimensions;
screening target data items in the client sample data, and determining effective risk indexes corresponding to the car loan risk dimension according to the target data items;
and constructing a vehicle loan pre-credit risk assessment system according to the effective risk indexes.
In one embodiment, the building of the car credit risk dimension according to the data of the plurality of car credit business dimensions and the car credit risk event library includes:
performing cluster analysis on data of a plurality of car credit service dimensions to obtain a plurality of cluster categories;
determining risk dimensions corresponding to all clustering categories according to the car loan risk event library;
and constructing the car loan risk dimension according to the risk dimensions corresponding to the plurality of clustering categories.
In one embodiment, the generating client sample data according to data of multiple car credit business dimensions includes:
combing the data of the multiple car credit service dimensions to obtain the service data of multiple customers;
determining a client label corresponding to each client according to the service data;
and determining the business data of the determined client label as the client sample data.
In one embodiment, the screening target data items in the client sample data includes:
carrying out univariate analysis on the client sample data to determine univariates which accord with risk identification conditions;
performing decision tree analysis on the client sample data to determine a combined variable meeting the risk identification condition;
performing special analysis on the client sample data to determine data items meeting the risk identification condition;
and determining the univariate meeting the risk identification condition, the combined variable and the data item meeting the risk identification condition as target data items.
In one embodiment, the method further comprises:
determining a data item to be derived in the data items of the client sample data;
constructing derived data items of a plurality of derived dimensions according to the data items to be derived;
and screening target data items in the constructed derivative data items and the client sample data.
In order to achieve the above object, according to a second aspect of the present application, there is provided a pre-car loan risk assessment method including:
obtaining a car loan request, wherein the car loan request carries a client identifier;
acquiring data to be evaluated corresponding to the client identification based on a plurality of vehicle credit service dimensions;
calling a pre-constructed vehicle credit pre-risk evaluation system, wherein the vehicle credit pre-risk evaluation system is constructed according to data of a plurality of vehicle credit service dimensions and a vehicle credit risk event library;
and performing risk assessment on the data to be assessed through the vehicle loan pre-credit risk assessment system, and determining a risk assessment result corresponding to the customer identification.
In order to achieve the above object, according to a third aspect of the present application, there is provided an apparatus for constructing a pre-loan risk assessment system, the apparatus including:
the dimension building module is used for building vehicle credit risk dimensions according to the data of the vehicle credit service dimensions and the vehicle credit risk event library;
the sample generation module is used for generating client sample data according to the data of the plurality of car credit service dimensions;
the index screening module is used for screening target data items from the client sample data and determining effective risk indexes corresponding to the car credit risk dimension according to the target data items;
and the system construction module is used for constructing a vehicle pre-loan risk assessment system according to the effective risk indexes.
In order to achieve the above object, according to a fourth aspect of the present application, there is provided a pre-car loan risk assessment apparatus including:
the communication module is used for acquiring a car loan request, and the car loan request carries a client identifier;
the second data acquisition module is used for acquiring service data corresponding to the client identification based on a plurality of vehicle credit service dimensions;
the system calling module is used for calling a pre-constructed vehicle credit pre-credit risk evaluation system, and the vehicle credit pre-credit risk evaluation system is constructed according to data of a plurality of vehicle credit service dimensions and a vehicle credit risk event library;
and the risk evaluation module is used for carrying out risk evaluation on the business data through the car loan pre-credit risk evaluation system and determining a risk evaluation result corresponding to the customer identification.
In order to achieve the above object, according to a fifth aspect of the present application, there is provided a computer device comprising a memory and a processor, the memory storing a computer program operable on the processor, the processor implementing the steps in the above method embodiments when executing the computer program.
According to a sixth aspect of the present application, there is provided a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the above-mentioned respective method embodiments.
According to the technical scheme, the vehicle credit risk dimension is constructed according to the data of the vehicle credit service dimensions and the vehicle credit risk event library, the client sample data is generated according to the data of the vehicle credit service dimensions, so that the target data items are screened from the client sample data, the effective risk indexes corresponding to the vehicle credit risk dimension are determined according to the target data items, and the vehicle credit pre-credit risk assessment system is constructed according to the effective risk indexes. Due to the fact that data of a plurality of car loan service dimensions are obtained, the vehicle risk dimension and the merchant risk dimension are increased on the basis of the personal risk dimension, a three-in-one pre-loan risk assessment system of 'people + cars + merchants' can be obtained, default risks of customers are assessed comprehensively and accurately, and accordingly the risk customers are intercepted.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a diagram of an exemplary environment in which a method for building a pre-loan risk assessment system is implemented;
FIG. 2 is a schematic flow chart illustrating a method for constructing a pre-loan risk assessment system according to an embodiment;
FIG. 3 is a schematic flow chart illustrating steps for constructing a car credit risk dimension based on data of a plurality of car credit business dimensions and a car credit risk event library according to one embodiment;
FIG. 4 is a schematic flow chart diagram illustrating the step of screening a target data item in client sample data in one embodiment;
FIG. 5 is a schematic flow chart illustrating a pre-loan risk assessment method according to an embodiment;
FIG. 6 is a block diagram showing an apparatus for constructing a pre-loan risk assessment system according to an embodiment;
FIG. 7 is a block diagram showing the structure of a pre-loan risk assessment apparatus according to an embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of this application and the above-described drawings, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
When the bank audits the car loan business, the bank needs to perform pre-loan risk assessment on the customer so as to determine whether the loan passes according to the risk assessment result. In the traditional mode, aiming at the assessment of the risk before car loan, no assessment system capable of comprehensively and accurately assessing the risk before car loan is available.
The method for constructing the pre-vehicle loan risk assessment system can be applied to the application environment shown in fig. 1. Wherein the terminal 102 and the server 104 communicate via a network. When the pre-car credit risk assessment system needs to be constructed, the terminal 102 may send a pre-car credit risk assessment system construction request to the server 104, and the server 104 obtains data of a plurality of car credit service dimensions according to the request. When the server 104 acquires data of a plurality of car credit service dimensions, the car credit risk dimensions are constructed according to the data of the car credit service dimensions and the car credit risk event library, so that client sample data is generated according to the data of the car credit service dimensions, target data items are screened from the client sample data, effective risk indexes of the car credit risk dimensions are generated according to the target data items, and a car credit pre-risk system is constructed according to the effective risk indexes. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.
Based on this, the present application proposes a method for constructing a risk assessment system before car loan, as shown in fig. 2, and the method is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
and step 202, constructing a car credit risk dimension according to the data of the car credit service dimensions and the car credit risk event library.
Vehicle lending is a main consumption form of modern automobile purchase, and refers to loan issued by lenders to purchase automobiles (including used cars) and comprises personal vehicle lending, automobile dealer vehicle lending and institution vehicle lending. The car credit business dimensions may include customer dimensions, vehicle dimensions, and merchant dimensions. The client refers to an applicant of the car loan, namely a borrower. May be an individual, distributor or organization. The vehicle is an automotive product to which car credits are directed. The commercial tenant refers to a seller of the vehicle, and when the customer is not personal or organized, the corresponding commercial tenant is an automobile dealer; when the customer is an automobile dealer, the corresponding merchant is another automobile dealer.
The data of the customer dimension may be referred to as customer data. Customer data refers to data associated with a customer, including customer base data, consumption data, credit data, revenue data, and the like. The data for the vehicle dimensions may be referred to as vehicle data, including the vehicle brand. Vehicle price, etc. The data of the merchant dimension may be referred to as merchant data, including business data, credit data, etc. of the merchant.
For car loan transactions, banks perform pre-loan risk assessment before issuing loans. Pre-credit risk may also be referred to as pre-credit admission risk. In the aspect of business process of risk assessment link before vehicle loan, the system can relate to a plurality of parties such as banks, clients, vehicles, automobile dealers and the like. In the aspect of risk data dimension, a plurality of data dimensions such as customer data, vehicle data, merchant data and the like are involved. In terms of fraud risk, a group fraud event is frequent. In order to comprehensively and accurately evaluate the risk before the car credit, a plurality of car credit service dimensions related to the risk evaluation before the car credit can be determined, so that data of each car credit service dimension, including customer data, vehicle data and merchant data, is obtained, the vehicle data and the merchant data are added on the basis of the customer data, the comprehensiveness of the data is improved from the source, and the multivariate of the car credit evaluation dimension is improved.
The vehicle loan risk event library is a database for recording the risk of the vehicle loan service in the whole loan period, and comprises a large amount of vehicle loan risk events. A car credit risk event refers to an event determined to be a car credit risk. The vehicle loan risk dimension refers to a basic dimension for evaluating the risk before the vehicle loan.
Before a car loan risk assessment system is constructed, a car loan risk dimension needs to be constructed, so that the risk assessment before the car loan is carried out on a client according to the constructed car loan risk dimension. The data of the car credit service dimensionality is scattered data, and in order to accurately construct the car credit risk dimensionality, the acquired data of the car credit service dimensionalities can be divided into multiple categories according to data types. For example, the plurality of categories may include transaction data, channel data, operational data, payment capability data, and payment intent data.
Because the car credit risk event in the car credit risk event library is an event determined as a car credit risk, the risk dimension corresponding to each category can be determined according to the risk item of the car credit risk event in the car credit risk event library, so that the car credit risk dimension can be constructed according to the risk dimensions corresponding to a plurality of categories. For example, the risk dimension to which the transaction data corresponds may be transaction authenticity. The risk dimension corresponding to the channel data may be a channel risk. The constructed car loan risk dimension may include transaction authenticity, repayment capacity, repayment willingness, channel risk, and operational risk.
Further, the car loan risk event library may be a special risk event library, and may include a business risk event library, a behavior risk event library, and a credit risk event library.
And step 204, generating sample data according to the data of the plurality of car loan service dimensions.
Sample data refers to a customer sample that contains a customer label. The customer tags may include good customers and bad customers.
The data for a plurality of car credit business dimensions includes: customer profile, credit assessment data, order data, vehicle data, credit score, merchant data, and the like. The server combs data of a plurality of car credit service dimensions, integrates data belonging to the same client, and accordingly obtains service data of a plurality of clients. And further determining a client label corresponding to each client according to the service data, and adding a corresponding client label for the client. Each customer corresponds to a customer label, and the customer label of each customer can be a good customer or a bad customer. The business data for each customer may include a plurality of data items. The data items may include a scholarly calendar, age, liabilities, merchants, etc.
And step 206, screening target data items from the client sample data, and determining effective risk indexes corresponding to the car loan risk dimension according to the target data items.
The server may screen the target data item from the client sample data according to a preset screening method. The preset screening method may include a univariate analysis method, a decision tree analysis method, and a special analysis method. A single data item with high risk identification rate in the client sample data can be determined through a univariate analysis method. The combined data item with higher risk identification rate in the client sample data can be determined by a decision tree analysis method. The data items of the pre-loan risk of the fixed customer base can be efficiently and accurately identified in the customer sample data through a special analysis method.
And associating the target data items screened by the various preset screening methods with the car credit risk dimensions, and determining effective risk indexes corresponding to the car credit risk dimensions. The effective risk indicator may include an indicator parameter and a corresponding indicator value. For example, the target data item of the screening is the debt of 1000 yuan, and the car credit risk dimension associated with the target data item is determined to be the debt condition in the repayment capability dimension.
And step 208, constructing a risk assessment system before the car loan according to the effective risk indexes.
The effective risk indicators are determined according to the target data items screened by the preset screening method, and therefore, the effective risk indicators also include single effective risk indicators and combined effective risk indicators. The relationship between the effective risk indicators is the relationship between the target data items. The server may generate a corresponding risk identification policy according to the relationship between the effective risk indicators. For example, a single effective risk indicator may generate a risk identification policy alone, and combining effective risk indicators may require combining multiple effective indicators to generate a risk identification policy.
And according to the generated risk identification strategy and a preset index threshold value, establishing a vehicle pre-loan risk assessment system so as to carry out vehicle pre-loan risk assessment on the client. When risk assessment is carried out through the constructed car loan pre-loan risk assessment system, the car loan pre-loan risk of the client can be assessed according to the risk identification strategy and the corresponding index threshold value.
In this embodiment, a vehicle credit risk dimension is constructed according to data of a plurality of vehicle credit service dimensions and a vehicle credit risk event library, client sample data is generated according to the data of the plurality of vehicle credit service dimensions, so that target data items are screened from the client sample data, effective risk indexes corresponding to the vehicle credit risk dimension are determined according to the target data items, and a vehicle credit pre-credit risk assessment system is constructed according to the effective risk indexes. Due to the fact that data of a plurality of car loan service dimensions are obtained, the vehicle risk dimension and the merchant risk dimension are increased on the basis of the personal risk dimension, a three-in-one pre-loan risk assessment system of 'people + cars + merchants' can be obtained, default risks of customers are assessed comprehensively and accurately, and accordingly the risk customers are intercepted.
In one embodiment, as shown in fig. 3, step 202, constructing a car credit risk dimension from data of a plurality of car credit business dimensions and a car credit risk event library, includes:
And step 304, determining risk dimensions corresponding to the clustering categories according to the car loan risk event library.
And step 306, constructing the car loan risk dimension according to the risk dimensions corresponding to the plurality of clustering categories.
The data for the car credit business dimension includes customer data, vehicle data, and merchant data. Since the data of the car credit service dimension is dispersed data, in order to accurately construct the car credit risk dimension, the acquired data of a plurality of car credit service dimensions can be subjected to cluster analysis, and the data with the same similarity are clustered into one cluster category, so that a plurality of cluster categories are obtained. For example, the plurality of cluster categories may include transaction data, channel data, operational data, repayment capacity data, and repayment intent data. Specifically, the server may perform cluster analysis on data of multiple vehicle and credit service dimensions by using multiple Clustering methods such as K-Means (K-Means), Spectral Clustering (Spectral Clustering), Hierarchical Clustering (Hierarchical Clustering), and the like.
And the server determines the corresponding dimension label of each cluster type according to the car loan risk event library. Dimension labels may include transaction authenticity, repayment capabilities, repayment willingness, channel risk, operational risk. Specifically, each cluster category may be compared with the car credit risk events in the car credit risk event library, and the risk dimension of the car credit risk event with the similarity greater than the threshold may be determined as the dimension label of the corresponding cluster category.
In order to refine the risk indexes under the dimension labels, car credit risk events in a car credit risk event library can be analyzed, the risk types of the car credit risk events are determined, the risk types are associated with the corresponding dimension labels, the first-level risk indexes corresponding to the dimension labels are determined, accordingly, the risk dimension corresponding to each clustering category is obtained according to the dimension labels and the first-level risk indexes corresponding to the dimension labels, and then the car credit risk dimension is constructed according to the risk dimensions corresponding to the clustering categories. For example, the primary risk indicators corresponding to transaction authenticity include purchases and cash-outs. The primary risk indicators corresponding to the repayment capacity comprise income level, liability condition, consumption preference, asset strength and fund tension. The first-level risk indexes corresponding to the repayment willingness comprise a performance record, a loss record, a black gray list and credit age. The first-level risk indexes corresponding to the channel risks comprise channel merchant risks and channel vehicle loan fraud. The first-level risk indexes corresponding to the operation risks comprise application information counterfeiting, zero first payment and high credit.
In this embodiment, the data of the car credit service dimension includes a plurality of dimensions such as customer data, vehicle data, merchant data, and the like, and the risk dimension corresponding to the data of the car credit service dimension can be accurately determined through the car credit risk event library, so that the car credit risk dimension is more comprehensive and accurate, and the risk control before car credit is more accurate.
In one embodiment, generating client sample data from data for a plurality of car credit business dimensions includes: combing the data of the multiple car credit service dimensions to obtain the service data of multiple customers; determining a client label corresponding to each client according to the service data; and determining the business data of the determined client label as the client sample data.
In order to determine an effective risk index corresponding to the car loan risk dimension, client sample data needs to be constructed to screen the effective risk index from the client sample data. Specifically, data of a plurality of car credit business dimensions are combed, and data of each customer are integrated together, so that business data of a plurality of customers are obtained. The business data of each customer may include 1) customer basic data such as gender, age, household location, etc.; 2) client credit data, such as a person credit message; 3) vehicle data, such as vehicle brand, vehicle price, etc.; 4) credit scores, such as FICO scores, medium integrity scores, and the like; 5) merchant information such as business data, credit data, etc.
And classifying the clients into two categories according to the service data, and determining whether each client is a good client or a bad client, so as to obtain the client label of each client. Specifically, default duration and default window period of each customer are determined in the business data, the default duration and the default window period are respectively matched with preset classification conditions, and a customer label corresponding to each customer is determined according to a matching result. Further, the time-out-of-date transfer matrix may be used to determine the length of the customer's default in the business data, such as 15 days. The default window period is determined by performing account age analysis on the business data, as in the previous 6 periods. The preset classification condition may be: good customers are those who never expire before the first 6 days, bad customers are those who are 15+ maximum expire before the first 6 days or those who are less than 15 days maximum expire before the first 6 days but have a cumulative number of expired times greater than or equal to 3. The remaining customers may be defined as gray customers for testing the constructed pre-car loan risk assessment system. And determining the business data of the determined client label as the client sample data. The client sample data comprises service data of good clients and service data of bad clients. Data items in the business data of bad customers may be determined to be a higher risk feature.
In this embodiment, data of a plurality of car credit business dimensions are sorted, and a corresponding client tag is determined according to the business data of the client obtained after the sorting, so that client sample data including the client tag is obtained, which is beneficial to subsequently and rapidly determining an effective risk index corresponding to a car credit risk dimension according to the client sample data.
In one embodiment, as shown in FIG. 4, step 206, screening the target data item in the client sample data includes:
And step 408, determining the univariate and the combined variable meeting the risk identification condition and the data item meeting the risk identification condition as target data items.
The client sample data comprises a plurality of data items, and the data items can comprise client basic data such as gender, age, household residence and the like; client credit data, such as a person credit message; vehicle data, such as vehicle brand, vehicle price, etc.; credit scores, such as FICO scores, medium integrity scores, and the like; merchant information such as business data, credit data, etc.
Since the client sample data comprises massive data items, in order to efficiently and accurately identify the risk before the car loan, the target data items can be screened out by respectively carrying out univariate analysis, decision tree analysis and special analysis on the client sample data, so that the effective risk index corresponding to the car loan risk dimension is determined according to the target data items. The order of univariate analysis, decision tree analysis and specific analysis is not limited herein.
Specifically, each data item in the client sample data may be called a single variable, and the single variable analysis is to determine the single variable with a high degree of lifting by comparing the overdue rate conditions of different profiles under the single variable of the client sample data, and determine the single variable with the high degree of lifting as the single variable meeting the risk identification condition.
The decision tree analysis method can be divided into score + variable decision tree analysis and variable + variable decision tree analysis. The score + variable decision tree analysis refers to that the score with the highest Value of the IV is crossed with other variables to serve as combined variables meeting the risk identification conditions by comparing the IV (Information Value) values of all credit scores in the client sample data. The variable + variable decision tree analysis means that the variables are crossed to determine data items capable of identifying fraudulent customers, such as recent slight overdue + debt, fund shortage + overdue.
The special analysis refers to an analysis mode for classifying the guest groups in the customer sample data according to different business modes and aiming at each guest group. The specialty analysis may include used car specialty analysis, high risk brand analysis, relationship network analysis, merchant analysis, and white house analysis. The special analysis of the used-car type refers to the characteristic that the risk of the used-car type customers is high by scoring the overdue rate and the credit rate in three aspects of basic customer information, transaction authenticity and repayment capacity of the used-car type customers in customer sample data and applying a univariate and decision tree cross analysis method. The high-risk brand analysis is to divide the vehicle brand into 7 boxes, for example, to determine the box with the highest overdue rate, and analyze the characteristics of the customer purchasing the high-risk vehicle type, such as the academic calendar, the age, the model, the liability, the credit record, the merchant and the like, according to the box. The relational network analysis means that the same corporate returns, the same contacts and the same corporate borrowers of all the clients are analyzed, the applicant is the credit post performance of the time difference between the corporate returns, the corporate borrowers and the contact application of other people and the main borrower application, and the characteristic that the risk recognition rate is high is determined. The merchant analysis is to select the characteristics of the customers with high overdue rate, such as the old, the foreign and the white households, and analyze whether the customers with the characteristics have concentrated packages when the customers enter packages with the merchant. And carrying out univariate and bivariate cross analysis on the characteristics of the customers with high overdue rate under the same merchant, and determining the characteristics with higher risk identification rate. And the white client can not judge the credit performance capability of the client, and the white client can select other characteristics with high overdue rate to perform cross analysis with the white client so as to determine the characteristics with higher risk identification rate.
Through the data item screening mode, univariates, combined variables and data items which meet risk identification conditions can be screened, and therefore all the screened data items are determined as target data items. The target data item refers to a data item capable of accurately or efficiently identifying the risk before the car loan.
In the embodiment, through carrying out univariate analysis, decision tree analysis and special analysis on the client sample data, multiple analysis methods are combined to screen the target data items, more comprehensive risk characteristics can be obtained, the vehicle credit risk dimensionality is enriched, effective risk indexes are generated, and the reliability and effectiveness of the vehicle credit pre-risk assessment system are improved.
In one embodiment, step 208, constructing a pre-loan risk assessment system based on the effective risk indicators, includes: generating a corresponding risk identification strategy according to the effective risk indexes; acquiring an index threshold corresponding to the effective risk index; and constructing a pre-vehicle loan risk assessment system according to the risk identification strategy and the index threshold.
The car loan risk dimension may include a plurality of dimension tags and a first level risk tag corresponding to each dimension tag. The effective risk indicator may be referred to as a secondary risk indicator for each dimension label in the car loan risk dimension. The effective risk index comprises an index parameter and a corresponding index value. The effective risk indexes are obtained by screening according to various analysis methods such as univariate analysis, decision tree analysis, special analysis and the like, and the effective risk indexes screened by each analysis method can be generated into a corresponding risk identification strategy. For example, a strong policy with high recognition efficiency is generated from univariates, a combined policy capable of recognizing risks more accurately is generated from combined variables, and a special policy is generated from data items screened by special analysis.
And setting a corresponding index threshold value for each effective risk index, and thus constructing a pre-car-loan risk assessment system according to the risk identification strategy and the index threshold value. The indicator thresholds may include a high risk threshold, a medium risk threshold, and a low risk threshold. And when the corresponding index threshold value is reached, determining the risk assessment result of the client according to the index threshold value.
In this embodiment, since the effective risk indicators are obtained by screening through a plurality of analysis methods, the identification relationship between the indicators can be determined, so that the generated risk identification strategy can perform multi-aspect risk identification according to the identification relationship between the indicators, and the reliability and effectiveness of risk identification are high. Meanwhile, the risk of the client can be quickly determined by setting the index threshold.
In one embodiment, the method further includes: acquiring an association relation and an identification sequence among the risk identification strategies; acquiring a result feedback mode corresponding to the risk identification strategy; and adding the incidence relation, the identification sequence and the result feedback mode into the car loan pre-loan risk assessment system.
The risk identification strategies are various, in order to avoid repeated strategies, the association relationship among the risk identification strategies can be identified, the association relationship is an alternative relationship, the risk identification strategies can be used alternatively, and the effect is the same. And the identification sequence of the risk identification strategy can be set according to actual needs. For example, risk identification by strong strategies, risk identification by special strategies, and risk identification by combined strategies may be performed. Further, the order of identification between policies may be determined according to the importance of risk identification.
A result feedback mode can be set in the risk assessment system before the vehicle loan and the loan, and the result feedback mode can comprise loan application refusal and manual processing transfer. For example, when the client is identified to have a risk, a message for refusing the loan application can be directly generated and fed back to the corresponding client, so that automatic feedback is realized. When the fact that the client has multiple risks is recognized, the risk evaluation result can be converted into manual processing, namely the risk evaluation result is sent to an auditor, the auditor audits the risk evaluation result, and whether the client is lended or not is judged.
In this embodiment, the association relationship, the identification order and the result feedback mode are added to the pre-car loan risk assessment system, so that the identification efficiency of the risk identification strategy can be improved, and the result feedback mode is set, so that the car loan request of the customer can be fed back quickly according to the risk assessment result.
In one embodiment, the method further comprises: determining a data item to be derived in the data items of the client sample data; constructing derived data items of a plurality of derived dimensions according to the data items to be derived; and screening target data items in the constructed derived data items and the client sample data.
The data items capable of being derived exist in the plurality of data items of the client sample data as data items to be derived. The data items to be derived may include time-recorded data items and category-recorded data items. The derived dimensions may include a temporal dimension, a spatial dimension, and an intersection of the temporal dimension and the spatial dimension. The data items with recorded time can comprise historical representation information, query record details and the like, each record has corresponding time, and the derivative data items can be constructed in the time dimension. The data items recorded by the classification can include account types, service types, query reasons and the like, and the derivative data items on different spatial dimensions can be constructed according to the required classification. The data items recorded with time and the data items recorded in the classification can be combined to construct derivative data items with the time dimension and the space dimension crossed. The server may screen the constructed derived data items and the client sample data for target data items.
In the embodiment, the derived data items of multiple derived dimensions are constructed according to the data items to be derived, so that the data volume of the sample is increased on the basis of original client sample data, more comprehensive target data items can be screened, and a comprehensive and reliable pre-car loan risk assessment system can be obtained.
In a second aspect of the present application, the present invention further provides a method for assessing risk before car loan, as shown in fig. 5, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
And step 504, acquiring data to be evaluated corresponding to the client identification based on the plurality of car credit service dimensions.
And step 508, performing risk assessment on the data to be assessed through the car loan pre-loan risk assessment system, and determining a risk assessment result corresponding to the customer identification.
The car loan request refers to a request for car loan made by a client, and is used for instructing the server to evaluate the risk of the client before car loan.
When the vehicle credit is required to be carried out, the server can obtain the vehicle credit request sent by the terminal, and the vehicle credit request is analyzed to obtain the client identification. The customer identification refers to a unique identification for distinguishing different customers, such as a customer name, a customer code and the like.
The plurality of car credit business dimensions include a customer dimension, a vehicle dimension, and a merchant dimension. And acquiring data of a customer dimension, a vehicle dimension and a merchant dimension corresponding to the customer identification, and determining the acquired data as data to be evaluated. The data to be evaluated may include: customer profile, credit assessment data, order data, vehicle data, credit score, merchant data, and the like.
The server stores a constructed pre-car-credit risk assessment system in advance, the pre-car-credit risk assessment system can be called after the data to be assessed corresponding to the client identification is obtained, and the pre-car-credit risk assessment system is constructed according to data of a plurality of car-credit service dimensions and a car-credit risk event library. The risk assessment method comprises the steps of performing risk assessment on data to be assessed according to a risk identification strategy in a risk assessment system before car loan, determining car loan risk dimensions corresponding to the data to be assessed, comparing the data to be assessed with index thresholds corresponding to effective risk indexes in the car loan risk dimensions, determining risks existing in a client according to the index thresholds matched with the index data to be assessed, and generating a risk assessment result. For example, when the age of the client in the data to be evaluated is 50, the index threshold corresponding to the age index is determined, wherein if the risk level is high corresponding to the age of 50, the risk level of the client is high. It is understood that the association relationship, the identification sequence, and the like before the risk identification policy in the pre-vehicle credit risk assessment system are also applicable in the pre-vehicle credit risk assessment process, and are not described herein again.
Further, when the client is identified to have a risk, a message of refusing the loan application can be directly generated and fed back to the corresponding client, so that automatic feedback is realized. When the fact that the client has multiple risks is recognized, the risk evaluation result can be converted into manual processing, namely the risk evaluation result is sent to an auditor, the auditor audits the risk evaluation result, and whether the client is lended or not is judged.
In this embodiment, the vehicle loan pre-loan risk assessment system is constructed according to data of a plurality of vehicle loan business dimensions and a vehicle loan risk event library, so that vehicle risk dimensions and merchant risk dimensions are increased on the basis of personal risk dimensions, a three-in-one human + vehicle + merchant pre-loan risk assessment system can be obtained, default risks of customers can be assessed comprehensively and accurately through the system, risk customers are intercepted, the passing rate of high-quality customers is increased, and the vehicle loan business transaction rate is increased.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
In a third aspect of the present application, as shown in fig. 6, the present invention further provides a device for constructing a pre-car loan risk assessment system, including: a dimension construction module 602, a sample generation module 604, an index screening module 606, and a system construction module 608, wherein:
and the dimension building module 602 is used for building the car credit risk dimension according to the data of the plurality of car credit business dimensions and the car credit risk event library.
And the sample generation module 604 is configured to generate client sample data according to the data of the multiple car credit service dimensions.
And the index screening module 606 is used for screening target data items from the client sample data and determining effective risk indexes corresponding to the car loan risk dimension according to the target data items.
And the system construction module 608 is used for constructing a pre-vehicle loan risk assessment system according to the effective risk indexes.
In one embodiment, the dimension construction module 602 is further configured to perform cluster analysis on data of a plurality of car credit service dimensions to obtain a plurality of cluster categories; determining risk dimensions corresponding to all clustering categories according to the car loan risk event library; and constructing the car loan risk dimension according to the risk dimensions corresponding to the plurality of clustering categories.
In one embodiment, the sample generation module 604 is further configured to comb data of multiple car credit business dimensions to obtain business data of multiple customers; determining a client label corresponding to each client according to the service data; and determining the business data of the determined client label as the client sample data.
In one embodiment, the index screening module 606 is further configured to perform univariate analysis on the client sample data to determine univariates that meet the risk identification condition; performing decision tree analysis on the client sample data to determine a combined variable meeting a risk identification condition; performing special analysis on client sample data to determine data items meeting risk identification conditions; and determining the univariate and the combined variable which meet the risk identification condition and the data item which meet the risk identification condition as target data items.
In one embodiment, the architecture module 608 is further configured to generate a corresponding risk identification policy according to the effective risk indicator; acquiring an index threshold corresponding to the effective risk index; and constructing a pre-vehicle loan risk assessment system according to the risk identification strategy and the index threshold.
In one embodiment, the above apparatus further comprises:
the strategy processing module is used for acquiring the incidence relation and the identification sequence among the risk identification strategies; acquiring a result feedback mode corresponding to the risk identification strategy; and adding the incidence relation, the identification sequence and the result feedback mode into a vehicle pre-loan risk assessment system.
In one embodiment, the above apparatus further comprises:
the data item derivation module is used for determining a data item to be derived in the data items of the client sample data; constructing derived data items of a plurality of derived dimensions according to the data items to be derived; and screening target data items in the constructed derived data items and the client sample data.
For specific limitations of the apparatus for constructing the risk assessment system before car lending, reference may be made to the above limitations of the method for constructing the risk assessment system before car lending, which are not described herein again. The modules in the device for constructing the pre-loan risk assessment system may be implemented in whole or in part by software, hardware, or a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In a fourth aspect of the present application, as shown in fig. 7, the present invention further provides a pre-car loan risk assessment apparatus, including: a communication module 702, a data acquisition module 704, a system invocation module 706, and a risk assessment module 708, wherein:
the communication module 702 is configured to obtain a car loan request, where the car loan request carries a client identifier.
And the data acquisition module 704 is configured to acquire service data corresponding to the client identifier based on the multiple car credit service dimensions.
And the system calling module 706 is used for calling a pre-constructed vehicle credit pre-credit risk evaluation system, and the pre-vehicle credit pre-credit risk evaluation system is constructed according to data of a plurality of vehicle credit service dimensions and a vehicle credit risk event library.
And the risk evaluation module 708 is used for performing risk evaluation on the business data through a pre-vehicle loan risk evaluation system and determining a risk evaluation result corresponding to the client identifier.
For the specific limitations of the pre-vehicle loan risk assessment apparatus, reference is made to the above limitations of the pre-vehicle loan risk assessment method, which are not described in detail herein. The modules in the pre-loan risk assessment device can be implemented in whole or in part by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In a fifth aspect of the present application, a computer device is provided, and the computer device may be a server, and the internal structure diagram thereof may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data of a construction method of a pre-car-loan risk assessment system or data of a pre-car-loan risk assessment method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a pre-car-loan risk assessment system method or a pre-car-loan risk assessment method.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In a sixth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the steps in the various embodiments described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A construction method of a risk assessment system before vehicle loan is characterized by comprising the following steps:
constructing a vehicle credit risk dimension according to the data of the vehicle credit service dimensions and the vehicle credit risk event library;
generating client sample data according to the data of the plurality of car loan service dimensions;
screening target data items in the client sample data, and determining effective risk indexes corresponding to the car loan risk dimension according to the target data items;
and constructing a vehicle loan pre-credit risk assessment system according to the effective risk indexes.
2. The method of claim 1, wherein constructing a car credit risk dimension from the data for the plurality of car credit business dimensions and the car credit risk event library comprises:
performing cluster analysis on data of a plurality of car credit service dimensions to obtain a plurality of cluster categories;
determining risk dimensions corresponding to all clustering categories according to the car loan risk event library;
and constructing the car loan risk dimension according to the risk dimensions corresponding to the plurality of clustering categories.
3. The method of claim 1, wherein generating customer sample data from data for a plurality of car credit business dimensions comprises:
combing the data of the multiple car credit service dimensions to obtain the service data of multiple customers;
determining a client label corresponding to each client according to the service data;
and determining the business data of the determined client label as the client sample data.
4. The method of claim 1, wherein said screening target data items in said client sample data comprises:
carrying out univariate analysis on the client sample data to determine univariates which accord with risk identification conditions;
performing decision tree analysis on the client sample data to determine a combined variable meeting a risk identification condition;
performing special analysis on the client sample data to determine data items meeting risk identification conditions;
and determining the univariate meeting the risk identification condition, the combined variable and the data item meeting the risk identification condition as target data items.
5. The method of any one of claims 1 to 4, further comprising:
determining a data item to be derived in the data items of the client sample data;
constructing derived data items of a plurality of derived dimensions according to the data items to be derived;
and screening target data items in the constructed derivative data items and the client sample data.
6. A method for assessing risk before vehicle loan is characterized by comprising the following steps:
obtaining a car loan request, wherein the car loan request carries a client identifier;
acquiring data to be evaluated corresponding to the client identification based on a plurality of vehicle credit service dimensions;
calling a pre-constructed vehicle credit pre-risk evaluation system, wherein the vehicle credit pre-risk evaluation system is constructed according to data of a plurality of vehicle credit service dimensions and a vehicle credit risk event library;
and performing risk assessment on the data to be assessed through the vehicle loan pre-credit risk assessment system, and determining a risk assessment result corresponding to the customer identification.
7. An apparatus for constructing a pre-loan risk assessment system, the apparatus comprising:
the dimension building module is used for building vehicle credit risk dimensions according to the data of the vehicle credit service dimensions and the vehicle credit risk event library;
the sample generation module is used for generating client sample data according to the data of the plurality of car credit service dimensions;
the index screening module is used for screening target data items from the client sample data and determining effective risk indexes corresponding to the car credit risk dimension according to the target data items;
and the system construction module is used for constructing a vehicle pre-loan risk assessment system according to the effective risk indexes.
8. A pre-loan risk assessment apparatus, the apparatus comprising:
the communication module is used for acquiring a car loan request, and the car loan request carries a client identifier;
the data acquisition module is used for acquiring service data corresponding to the client identification based on a plurality of vehicle credit service dimensions;
the system calling module is used for calling a pre-constructed vehicle credit pre-credit risk evaluation system, and the vehicle credit pre-credit risk evaluation system is constructed according to data of a plurality of vehicle credit service dimensions and a vehicle credit risk event library;
and the risk evaluation module is used for carrying out risk evaluation on the business data through the car loan pre-credit risk evaluation system and determining a risk evaluation result corresponding to the customer identification.
9. A computer device comprising a memory and a processor, the memory storing a computer program operable on the processor, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110834150.2A CN113592623A (en) | 2021-07-20 | 2021-07-20 | Construction method of risk assessment system before vehicle loan and credit and risk assessment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110834150.2A CN113592623A (en) | 2021-07-20 | 2021-07-20 | Construction method of risk assessment system before vehicle loan and credit and risk assessment method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113592623A true CN113592623A (en) | 2021-11-02 |
Family
ID=78249438
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110834150.2A Pending CN113592623A (en) | 2021-07-20 | 2021-07-20 | Construction method of risk assessment system before vehicle loan and credit and risk assessment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113592623A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944772A (en) * | 2017-12-27 | 2018-04-20 | 深圳市轱辘车联数据技术有限公司 | Car based on block chain borrows risk information processing method and processing device |
| CN108876133A (en) * | 2018-06-07 | 2018-11-23 | 中国平安人寿保险股份有限公司 | Risk assessment processing method, device, server and medium based on business information |
| WO2019080407A1 (en) * | 2017-10-25 | 2019-05-02 | 深圳壹账通智能科技有限公司 | Credit evaluation method, apparatus and device, and computer readable storage medium |
| CN110276552A (en) * | 2019-06-21 | 2019-09-24 | 深圳前海微众银行股份有限公司 | Risk analysis method, device, equipment and readable storage medium storing program for executing before borrowing |
| WO2020037942A1 (en) * | 2018-08-20 | 2020-02-27 | 平安科技（深圳）有限公司 | Risk prediction processing method and apparatus, computer device and medium |
| CN111325248A (en) * | 2020-02-10 | 2020-06-23 | 深圳华策辉弘科技有限公司 | Method and system for reducing pre-loan business risk |
| CN111932367A (en) * | 2020-08-13 | 2020-11-13 | 中国银行股份有限公司 | Pre-credit evaluation method and device |
| CN112215702A (en) * | 2020-10-14 | 2021-01-12 | 深圳市欢太科技有限公司 | Credit risk assessment method, mobile terminal and computer storage medium |
| CN112232950A (en) * | 2020-12-10 | 2021-01-15 | 银联商务股份有限公司 | Loan risk assessment method and device, equipment and computer-readable storage medium |
-
2021
- 2021-07-20 CN CN202110834150.2A patent/CN113592623A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019080407A1 (en) * | 2017-10-25 | 2019-05-02 | 深圳壹账通智能科技有限公司 | Credit evaluation method, apparatus and device, and computer readable storage medium |
| CN107944772A (en) * | 2017-12-27 | 2018-04-20 | 深圳市轱辘车联数据技术有限公司 | Car based on block chain borrows risk information processing method and processing device |
| CN108876133A (en) * | 2018-06-07 | 2018-11-23 | 中国平安人寿保险股份有限公司 | Risk assessment processing method, device, server and medium based on business information |
| WO2020037942A1 (en) * | 2018-08-20 | 2020-02-27 | 平安科技（深圳）有限公司 | Risk prediction processing method and apparatus, computer device and medium |
| CN110276552A (en) * | 2019-06-21 | 2019-09-24 | 深圳前海微众银行股份有限公司 | Risk analysis method, device, equipment and readable storage medium storing program for executing before borrowing |
| CN111325248A (en) * | 2020-02-10 | 2020-06-23 | 深圳华策辉弘科技有限公司 | Method and system for reducing pre-loan business risk |
| CN111932367A (en) * | 2020-08-13 | 2020-11-13 | 中国银行股份有限公司 | Pre-credit evaluation method and device |
| CN112215702A (en) * | 2020-10-14 | 2021-01-12 | 深圳市欢太科技有限公司 | Credit risk assessment method, mobile terminal and computer storage medium |
| CN112232950A (en) * | 2020-12-10 | 2021-01-15 | 银联商务股份有限公司 | Loan risk assessment method and device, equipment and computer-readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 杜一谦;: "消费信贷智能决策模型***设计与实现", 中国新技术新产品, no. 13, pages 18 - 20 * |
| 许文: "关于商业银行信用风险评估方法的研究", 辽宁师范大学学报(自然科学版), no. 01, pages 36 - 38 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876133B (en) | Risk assessment processing method, device, server and medium based on business information | |
| CN109767322B (en) | Suspicious transaction analysis method and device based on big data and computer equipment | |
| KR102134792B1 (en) | Method for providing used goods trade service using fraud detection and appraisal based on blockchain with safe transaction | |
| CN111861174B (en) | Credit assessment method for user portrait | |
| US20120150786A1 (en) | Multidimensional risk-based detection | |
| US20070174214A1 (en) | Integrated fraud management systems and methods | |
| Butler et al. | Racial discrimination in the auto loan market | |
| KR20180060044A (en) | Security System for Cloud Computing Service | |
| CN110246030A (en) | In many ways risk management method, terminal, device and storage medium after the loan to link | |
| CN110619065A (en) | Resource scheduling service processing method and device, computer equipment and storage medium | |
| CN109903045B (en) | Behavior track monitoring method, device, computer equipment and medium | |
| US20230206323A1 (en) | Intelligent data matching and validation system | |
| KR20180060005A (en) | Security System for Cloud Computing Service | |
| CN111899100A (en) | Service control method, device and equipment and computer storage medium | |
| CN115082225A (en) | Enterprise financing risk assessment method and device | |
| CN112163944A (en) | Loan qualification scoring method and device for customer, computer equipment and storage medium | |
| Dimitras et al. | Evaluation of empirical attributes for credit risk forecasting from numerical data | |
| CN116911882B (en) | Insurance fraud prevention prediction method and system based on machine learning | |
| CN113269629A (en) | Credit limit determining method, electronic equipment and related product | |
| CN117575773A (en) | Method, device, computer equipment and storage medium for determining service data | |
| KR20170037299A (en) | System and Method for Real time based Credit Risk Analysis using the Integrated Account Information | |
| CN115564591A (en) | Financing product determination method and related equipment | |
| CN113592623A (en) | Construction method of risk assessment system before vehicle loan and credit and risk assessment method | |
| US20140279395A1 (en) | System and methods for providing least cost data acquisition for financial decisions | |
| CN114331728A (en) | Security analysis management system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |