Order Behavior Risk Assessment System, Method and Storage Medium Based on Big Data

Abstract

The present invention relates to the field of pan-financial anti-fraud, specifically a risk assessment system, method and storage medium based on big data for orders, which are used to solve the problems of lacking the second assessment during order processing, missing the analysis of behavioral characteristics during the order generation process, resulting in inaccurate risk prevention, and only conducting risk assessment on orders, unable to extend to the assessment of customer groups, products and channels. The present invention obtains the application information during customer review and the risk control information belonging to the order supplemented during order processing. By comparing the two risk control information, in addition to conducting risk assessment during application review for an order, a second assessment can also be carried out between application review and business processing. When a risk anomaly occurs during the second assessment, payment for the order can be intercepted in a timely manner, thereby avoiding financial losses and preventing potential credit risks in advance, and being able to prevent risks more precisely.

Description

Technical Field

[0001] The present invention relates to the field of pan-financial anti-fraud, and specifically to an order behavior risk assessment system, method and storage medium based on big data. Background Art

[0002] Pan-finance is a relatively broad concept. It is not only limited to traditional financial fields such as banks, securities and insurance, but also covers a series of industries and activities closely related to finance. First of all, Internet finance is an important part of pan-finance, including emerging financial models such as third-party payment platforms, online lending, and crowdfunding. Secondly, consumer finance is also within the scope of pan-finance, such as credit card business, consumer loans, etc. Moreover, supply chain finance is also an important part that cannot be ignored. By integrating logistics, capital flow and information flow in the supply chain, it provides financing and risk management services for enterprises on the supply chain;

[0003] In the prior art, pan-financial anti-fraud and risk assessment are both applied in online or offline modes. In the traditional offline mode, offline card acceptance is carried out, and the information is sent back to the credit review department for review, and it is directly processed after qualification review, without real-time requirements; in the pure online mode, only the information submitted online and the queryable data information are considered, without offline information. The traditional offline mode uses more expert experience rules, and the online mode uses more supervised algorithms, and generally conducts risk assessment on orders, and cannot extend to the assessment of customer groups, products and channels;

[0004] Therefore, a risk assessment system is needed that can perform risk assessment on the characteristics during the period between qualification review and business processing, intercept risks, and prevent potential usage risks in advance;

[0005] In view of the above technical problems, the present application proposes a solution. Summary of the Invention

[0006] The present invention obtains the risk control information during customer qualification review and the order-related risk control information supplemented during order processing. Through the comparison of the two risk control information, in addition to performing risk assessment during application review for an order, a secondary assessment can also be carried out between application review and business processing. When a risk anomaly occurs in the secondary assessment, the order can be intercepted in a timely manner, thereby avoiding losses caused by the order, preventing potential usage risks in advance, being able to more precisely prevent risks, solving the problems of lacking the second assessment during order processing, insufficiently precise risk prevention, and only performing risk assessment on orders and being unable to extend to the assessment of customer groups, products and channels, and proposes an order behavior risk assessment system, method and storage medium based on big data.

[0007] The object of the present invention can be achieved through the following technical solutions:

[0008] A risk assessment system for order behavior based on big data, including an order acquisition module, which is used to acquire orders that have passed the review and obtain order information. The order information includes order attribution information and initial order risk control information. The order acquisition module can also update the order risk control information during order processing to obtain applied risk control information;

[0009] An order behavior analysis module, which compares the initial risk control information with the applied risk control information to obtain the change degree of various specific factors in the order risk control information;

[0010] An order risk control module, which obtains the change degree of various factors in the order risk control information and calculates the risk control eigenvalue through a preset model algorithm to generate a risk control pass signal or a risk control fail signal;

[0011] A result extension module, which creates a three-dimensional solid model containing multiple small regions composed of order attribution information and performs labeled management on different regions in the three-dimensional solid model according to the risk control pass signal or the risk control fail signal to obtain the risk degree corresponding to each region;

[0012] A historical database, which is used to store historical order information.

[0013] As a preferred embodiment of the present invention, the order attribution information obtained by the order acquisition module includes customer qualifications, product types, and product channels, and the order risk control information includes order geographical location, order customer group value, order application area, and order time.

[0014] As a preferred embodiment of the present invention, the order behavior analysis module calculates the straight-line distance between the order geographical location in the initial risk control information and the order geographical location in the applied risk control information, and corrects the straight-line distance through a regional weight coefficient to obtain the geographical location deviation;

[0015] The order behavior analysis module obtains the historical product records of the order users, performs weighted averaging on the order values in the historical product records to obtain the average order value, where the weights increase in the order of the order time, and calculates the difference between the order value of the current product and the average order value in the historical product records to obtain the product deviation.

[0016] As a preferred embodiment of the present invention, the order behavior analysis module obtains the product area and product type of the order, and obtains the number of orders of the same product type in the current area within a set time period through the historical database, and uses the number of orders as an aggregation index;

[0017] The order behavior analysis module calculates the difference between the order time in the initial risk control information and the order time in the applied risk control information to obtain the time difference of the order;

[0018] The order behavior analysis module obtains the average value of the time difference of the same product type through the historical database, compares the average value of the time difference with the time difference of the order, and obtains the time difference offset.

[0019] As a preferred embodiment of the present invention, the order behavior analysis module sends the time difference offset, the aggregation index, the product offset degree, and the geographical location deviation to the order risk control module. The order risk control module records the received data as influencing factors. The order risk control module performs import analysis on the influencing factors through preset supervised algorithms and unsupervised algorithms, obtains the risk control eigenvalue through the analysis result, and compares the risk control eigenvalue with the set characteristic threshold, and generates a risk control failure signal or a risk control pass signal according to the comparison result;

[0020] The order risk control module sends the risk control failure signal or the risk control pass signal to the result extension module, and at the same time sends the corresponding customer qualification, product type, and product channel to the result extension module.

[0021] As a preferred embodiment of the present invention, the result extension module creates a three-dimensional coordinate system, divides multiple paragraphs on the XYZ axes of the three-dimensional coordinate system, divides the customer qualification, each product type, and each product channel into multiple stages, and assigns each stage to each paragraph on the X, Y, and Z axes respectively to obtain a three-dimensional solid model containing multiple small regions;

[0022] When the result extension module obtains a risk control failure signal or a risk control pass signal each time, it obtains the order attribution information corresponding to the risk control failure signal or the risk control pass signal, and locates to the corresponding area in the three-dimensional solid model according to the order attribution information;

[0023] If the obtained is a risk control failure signal, a high-risk label is added to the corresponding area. If the obtained is a risk control pass signal, a safety label is added to the corresponding area;

[0024] The result extension module calculates the proportion of the number of high-risk labels in each small region of the three-dimensional solid model. If the proportion of the number of high-risk labels is greater than the set threshold, the area is recorded as a high-risk area. If the proportion of the number of high-risk labels is not greater than the set threshold, the area is recorded as a low-risk area.

[0025] The order risk assessment method based on the big data model is applicable to the above-mentioned order behavior risk assessment system based on big data. The method includes the following steps:

[0026] Step 1: Obtain order information;

[0027] Step 2: Refresh application risk control information;

[0028] Step 3: Differentiated comparison of order risk control information;

[0029] Step 4: Judge order risk;

[0030] Step 5: Statistically expand order risk results.

[0031] A computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, an order risk assessment method based on a big data model is implemented.

[0032] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0033] 1. By conducting a second assessment during order processing, the present invention can more precisely prevent risks. Specifically, the application information obtained during customer review is used as risk control information, and the risk control information belonging to the order supplementarily obtained during order processing is used. Through the comparison of the two risk control information, in addition to the risk assessment during application review for an order, a secondary assessment can also be performed between application review and business processing. When a risk anomaly occurs during the secondary assessment, the order can be intercepted in a timely manner, thereby avoiding losses to funds and preventing potential credit risks in advance.

[0034] 2. By deeply mining and utilizing the risk assessment results during order processing, the present invention realizes the potential risk and quantitative assessment of product types, user qualifications, and product channels, and further uses the discovered important features for monitoring and early warning, while supporting the formulation of corresponding risk control strategies, thereby improving the accuracy of risk assessment during the review period and increasing the depth of utilization of risk control data for the secondary assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings.

[0036] Figure 1 is the system block diagram of the present invention;

[0037] Figure 2 is the system flowchart of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0038] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0039] Example 1:

[0040] Please refer to Figure 1 - Figure 2 As shown, the order behavior risk assessment system based on big data includes an order acquisition module, an order behavior analysis module, an order risk control module, a result extension module, and a historical database. The order acquisition module obtains the orders that have passed the review through offline or online channels, and uploads the order information after passing the review to the order behavior analysis module. The order information includes order attribution information and order risk control information. Among them, the order attribution information includes customer qualifications, product types, and product channels. The order risk control information includes order geographical location, order customer group value, order application area, and order time. Among them, the order geographical location is the specific location when the order is applied and processed. The order customer group value is the value of the order applied and processed;

[0041] When the order acquisition module obtains the orders that have passed the review, it records the order risk control information to obtain the initial risk control information. When the order business is processed, it updates the order risk control information to obtain the applied risk control information;

[0042] When the order acquisition module obtains the initial risk control information and the applied risk control information, it sends the initial risk control information and the applied risk control information to the order behavior analysis module for analysis;

[0043] The order behavior analysis module analyzes the geographical location of the order, calculates the difference between the order geographical location in the initial risk control information and the order geographical location in the applied risk control information to obtain the geographical location deviation. The method of differential calculation is as follows:

[0044] The order behavior analysis module records the geographical location in the initial risk control information as the initial location, records the geographical location in the applied risk control information as the applied location, calculates the straight-line distance between the initial location and the applied location, and records it as L. The straight-line distance L is corrected by the regional weight coefficient to obtain the geographical location deviation LD. LD = s * L, where s is the regional weight coefficient. When the initial location and the applied location are in the same province, the regional weight coefficient takes the value of s1. If the initial location and the applied location are in different provinces, the value of the regional weight coefficient is s2, where s1 < s2;

[0045] The method for the order behavior analysis module to obtain the migration of the customer group value is as follows:

[0046] Obtain the historical product records of the order users through the historical database, perform weighted averaging on the order values in the historical product records to obtain the average order value, and calculate the difference between the order value of the current product and the average order value in the historical product records to obtain the product deviation. The method for performing weighted averaging on the order values in the historical product records is as follows:

[0047] Record the order values in the historical product records in chronological order as Ji, assign weights qi to different historical products, where i = 1, 2, 3..., n, to obtain the average order value J0. Among them, the value of the weight qi increases as i increases, so that when averaging the order values of historical products, the historical change trend of the order values is taken into consideration.

[0048] The order behavior analysis module obtains the product area and product type of the order, and obtains the order quantity of the same product type in the current area within the set time period through the historical database, and takes the order quantity as the aggregation index.

[0049] The order behavior analysis module obtains the order times in the initial risk control information and the applied risk control information, and calculates the difference between the order time in the initial risk control information and the order time in the applied risk control information to obtain the time difference of the order.

[0050] The order behavior analysis module obtains the average value of the time differences of the same product type through the historical database, compares the average value of the time differences with the time difference of the order to obtain the time difference deviation.

[0051] The order behavior analysis module sends the time difference deviation, the aggregation index, the product deviation degree, and the geographical location deviation to the order risk control module. The order risk control module records the received data as influencing factors. The order risk control module performs import analysis on the influencing factors through preset supervised algorithms and unsupervised algorithms, obtains the risk control eigenvalue through the analysis result, and compares the risk control eigenvalue with the set feature threshold. If the risk control eigenvalue is greater than the set risk control threshold, a risk control failure signal is generated. If the risk control eigenvalue is less than the set risk control threshold, a risk control pass signal is generated.

[0052] The order risk control module sends the risk control failure signal or the risk control pass signal to the result extension module, and at the same time sends the corresponding customer qualification, product type, and product channel to the result extension module.

[0053] Embodiment 2:

[0054] Please refer to Figure 1 - Figure 2 As shown, the result extension module creates a three-dimensional coordinate system, divides it into multiple segments on the XYZ axes of the three-dimensional coordinate system, divides the customer qualification into multiple stages, assigns each stage to each segment on the X-axis, divides each product type to each segment on the Y-axis, and divides each product channel to each segment on the Z-axis, thereby obtaining a three-dimensional solid model containing multiple small areas.

[0055] When the result extension module obtains a risk control failure signal or a risk control passing signal each time, it obtains the corresponding customer qualifications, product types, and product channels in the risk control failure signal or the risk control passing signal, and locates them to the corresponding areas in the three-dimensional model according to the customer qualifications, product types, and product channels;

[0056] If the obtained signal is a risk control failure signal, a high-risk label is added to the corresponding area. If the obtained signal is a risk control passing signal, a safety label is added to the corresponding area;

[0057] The result extension module updates the three-dimensional model in real time, calculates the proportion of the number of high-risk labels in each small area of the three-dimensional model. If the proportion of the number of high-risk labels is greater than the set threshold, the area is recorded as a high-risk area. If the proportion of the number of high-risk labels is not greater than the set threshold, the area is recorded as a low-risk area.

[0058] The result extension module sends the three-dimensional model to the management platform through the network. When the management platform obtains an order to be audited, it locates in the three-dimensional model according to the customer qualifications, product types, and product channels of the order. If the located area is a high-risk area, the order is marked as a high-risk order. If the located area is a low-risk area, the order is marked as a low-risk order, so as to realize the risk degree prediction of the pre-audit of the order.

[0059] Embodiment 3:

[0060] Please refer to Figure 1 - Figure 2 As shown in the figure, an order risk assessment method based on a big data model, the method includes the following steps:

[0061] Step 1: Obtain the order attribution information and order risk control information of the orders passed in the audit to obtain the initial risk control information;

[0062] Step 2: When handling the business of the orders passed in the audit, refresh the risk control information to which the order belongs to obtain the applied risk control information;

[0063] Step 3: Compare various influencing factors in the initial risk control information and the applied risk control information to obtain the change of influencing factors;

[0064] Step 4: Take the change of influencing factors as an influencing factor, import supervised algorithms and unsupervised algorithms for different algorithm analyses to obtain risk control eigenvalue, and compare the risk control eigenvalue with the set threshold to confirm the order risk, so as to realize the interception and passing of the order;

[0065] Step 5: Classify and analyze the order data according to the attribution information of the order and the risk confirmation result of the order, provide data support for the preliminary review of the order, and realize the risk prediction during the order review period.

[0066] Embodiment 4:

[0067] Please refer to Figure 1 - Figure 2 As shown, the present invention also proposes a storage medium for order behavior risk assessment based on big data, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned method for order behavior risk assessment based on big data is realized. Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to the computer program.

[0068] The foregoing computer program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments. The computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages and also conventional procedural programming languages. The program code can be completely executed on a system server or cloud service, provided as an independent application function module with an external interface service, and interact with other business systems or application processes for information interaction or embedded integration.

[0069] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor limit the present invention to only the specific embodiments. Obviously, according to the content of this specification, many modifications and variations can be made. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the present invention, so that those skilled in the art in the relevant technical field can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An order behavior risk assessment system based on big data, characterized in that, It includes an order acquisition module. The order acquisition module obtains the orders that have passed the review through offline or online channels, and uploads the order information after passing the review to the order behavior analysis module. The order information includes order attribution information and order risk control information. Among them, the order attribution information includes customer qualification, product type, and product channel. The order risk control information includes order geographical location, order customer group value, product area of the order, and order time. Among them, the order geographical location is the specific location at the time of order application and order handling, and the order customer group value is the value of the applied and handled order; When the order acquisition module obtains the orders that have passed the review, it records the order risk control information to obtain the initial risk control information. When the order business is being processed, it updates the order risk control information to obtain the applied risk control information; An order behavior analysis module. The order behavior analysis module compares the initial risk control information and the applied risk control information to obtain the change degree of various specific factors in the order risk control information; The order behavior analysis module calculates the straight-line distance between the order geographical location in the initial risk control information and the order geographical location in the applied risk control information, and corrects the straight-line distance through the regional weight coefficient to obtain the geographical location deviation; The order behavior analysis module obtains the historical product records of the order user, performs weighted average on the order values in the historical product records to obtain the order value mean. Among them, the values of the weights increase in the order time sequence, and calculates the difference between the order value of the current product and the order value mean in the historical product records to obtain the product deviation; The order behavior analysis module obtains the product area and product type of the order, and obtains the number of orders of the same product type in the current area within the set time period through the historical database, and uses the number of orders as the aggregation index; The order behavior analysis module calculates the difference between the order time in the initial risk control information and the order time in the applied risk control information to obtain the time difference of the order; The order behavior analysis module obtains the mean value of the time difference of the same product type through the historical database, and compares the mean value of the time difference with the time difference of the order to obtain the time difference deviation; The order behavior analysis module sends the time difference deviation, the aggregation index, the product deviation, and the geographical location deviation to the order risk control module. The order risk control module records the received data as influencing factors. The order risk control module imports and analyzes the influencing factors through the preset supervised algorithm and unsupervised algorithm, obtains the risk control eigenvalue through the analysis result, and compares the risk control eigenvalue with the set feature threshold, and generates a risk control failure signal or a risk control pass signal according to the comparison result; An order risk control module. The order risk control module obtains the change degree of various factors in the order risk control information, and calculates the risk control eigenvalue through the preset model algorithm to generate a risk control pass signal or a risk control failure signal; The order risk control module sends the risk control failure signal or the risk control pass signal to the result extension module, and at the same time sends the corresponding customer qualification, product type, and product channel to the result extension module; A result extension module, which creates a three-dimensional model composed of order attribution information and includes multiple small regions, and performs labeled management on different regions in the three-dimensional model according to the risk control pass signal or the risk control fail signal to obtain the risk level corresponding to each region; A historical database, which is used to store historical order information.

2. The order behavior risk assessment system based on big data according to claim 1, wherein The result extension module creates a three-dimensional coordinate system and divides it into multiple paragraphs on the XYZ axes of the three-dimensional coordinate system. The customer qualifications, each product type, and each product channel are divided into multiple stages, and each stage is respectively assigned to each paragraph on the X, Y, and Z axes to obtain a three-dimensional model containing multiple small regions; Each time the result extension module obtains a risk control fail signal or a risk control pass signal, it obtains the corresponding order attribution information in the risk control fail signal or the risk control pass signal, and locates it to the corresponding region in the three-dimensional model according to the order attribution information; If the obtained signal is a risk control fail signal, a high-risk label is added to the corresponding region. If the obtained signal is a risk control pass signal, a safety label is added to the corresponding region; The result extension module calculates the proportion of the number of high-risk labels in each small region of the three-dimensional model. If the proportion of the number of high-risk labels is greater than the set threshold, the region is recorded as a high-risk region. If the proportion of the number of high-risk labels is not greater than the set threshold, the region is recorded as a low-risk region.

3. A method for risk assessment of order behavior based on big data, applicable to the system for risk assessment of order behavior based on big data according to claim 2, characterized in that, The method includes the following steps: Step 1: Order information acquisition; Step 2: Application of risk control information refresh; Step 3: Differential comparison of order risk control information; Step 4: Order risk judgment; Step 5: Order risk result statistics and extension.

4. A computer-readable storage medium applicable to the big data-based order behavior risk assessment method described in claim 3, on which a computer program is stored. When the computer program is executed by a processor, the big data-based order behavior risk assessment method is implemented.

Images