User credit fraud risk assessment method and system based on LBS data

Abstract

The user credit fraud risk assessment method and system based on LBS data provided by the present application include: obtaining the credit application history information within the credit business scope, including the user credit application time and the user credit application LBS data; encoding the regional information to obtain all regional codes within the credit business scope; obtaining all community numbers within the credit business scope according to the user credit application time and regional code; obtaining the proportion of black samples in each region and the proportion of communities with synchronized black behaviors in each region according to all regional codes and community numbers and historical credit application information obtained within the credit business scope; obtaining the credit fraud score of the user to be evaluated according to the proportion of black samples in each region and the proportion of communities with synchronized black behaviors in each region. The present application analyzes the aggregated behavior of LBS data in the user application stage to identify fraudulent users as accurately as possible without affecting the credit application approval rate.

Description

Technical Field

[0001] The present application relates to the field of anti-fraud technology for credit applications, and in particular to a method and system for assessing user credit fraud risk based on LBS data. Background Art

[0002] In the field of credit risk control, 80% of the risk control core lies in the pre-loan credit approval stage. Risk identification in the credit approval stage is crucial to the overall asset quality, and fraud risk often causes losses to the assets of financial institutions due to improper purposes and behaviors such as false applications by applicants. Therefore, the identification of fraud risks is particularly important, and the identification of group fraud is the top priority. Group fraud is organized and large-scale, causing great harm to financial business, and is full of criminal behavior. The analysis and identification of fraud gangs is of great significance to credit financial institutions.

[0003] At present, all financial institutions use big data and artificial intelligence to identify gang fraud, and longitude and latitude data is one of the most commonly used data. Longitude and latitude data is simple and efficient, and can intuitively show the aggregation of groups from the physical location. When used together with other means, it can often achieve certain results. At present, the processing of longitude and latitude data usually uses the GeoHash algorithm for regional coding. GeoHash calculation is simple and efficient, and can be used for coding a large amount of location data, but its shortcomings are also obvious. GeoHash is mainly based on Z curves for grid division, and there are jump points, that is, the coding prefix is ​​the same but the actual physical location is far apart. At the same time, GeoHash has only 12 levels, and the accuracy of each level of grid division varies greatly, which is not conducive to user selection. The accuracy and range may be difficult to meet the usage requirements at the same time. Summary of the invention

[0004] The present application provides a user credit fraud risk assessment method based on LBS data, which can solve the technical problem that the accuracy and scope of credit fraud analysis based on latitude and longitude data in the prior art are difficult to meet the usage requirements at the same time.

[0005] In a first aspect, the present application provides a method for assessing user credit fraud risk based on LBS data, comprising the following steps:

[0006] Obtain credit application history information within the scope of credit business, including user credit application time and user credit application LBS (Location Based Service) data;

[0007] Encode the regional information in the LBS data of the user's credit application to obtain all regional codes within the credit business scope;

[0008] According to the user's credit application time and area code, obtain all community numbers within the credit business scope;

[0009] Based on all the regional codes and community numbers within the scope of the obtained credit business and historical credit application information, the percentage of black samples in each region and the percentage of communities with black behaviors in each region are statistically obtained;

[0010] The credit fraud score of the user to be evaluated is obtained based on the proportion of black samples in each area and the proportion of black behavior synchronized communities in each area.

[0011] In combination with the first aspect, in one implementation, encoding the area information in the LBS data of the user's credit application to obtain all area codes within the credit business scope specifically includes the following steps:

[0012] The area code of each applicant is obtained by calculating based on the LBS data of the applicant using the Google S2 algorithm.

[0013] In combination with the first aspect, in one implementation, obtaining all community numbers within the credit business scope according to the user's credit application time and area code specifically includes the following steps:

[0014] For users in the same coding area, a corresponding time synchronization behavior relationship diagram is generated based on the user's credit application time and time synchronization range in the credit application history information;

[0015] The community discovery algorithm is used to divide the time synchronization behavior relationship graph into communities and obtain all community numbers within the scope of the credit business.

[0016] In combination with the first aspect, in one implementation, the method of obtaining the percentage of black samples in each region and the percentage of black behavior synchronization communities in each region based on all regional codes and community numbers and historical credit application information within the obtained credit business scope specifically includes the following steps:

[0017] According to all regional codes within the credit business scope, the percentage of black samples in each region is counted;

[0018] According to the community numbers within the credit business scope, the percentage of black samples in each community is counted;

[0019] According to the proportion of black samples in each area and the proportion of black samples in each community, the proportion of communities with synchronized black behaviors in each area is calculated.

[0020] In combination with the first aspect, in one implementation, the calculation of the proportion of black behavior synchronized communities in each region based on the proportion of black samples in each region and the proportion of black samples in each community specifically includes the following steps:

[0021] When the proportion of black samples in a community is greater than the proportion of black samples in the overall area where the community is located, the community is judged to be a black behavior synchronization community, otherwise it is judged to be a good behavior synchronization community;

[0022] Count the percentage of black behavior synchronous communities in each region.

[0023] In combination with the first aspect, in one implementation, obtaining the credit fraud score of the user to be evaluated according to the proportion of the number of black samples in each area and the proportion of the number of black behavior synchronized communities in each area specifically includes the following steps:

[0024] According to the proportion of black samples in each region and the proportion of black behavior synchronous communities in each region, the fraud risk level of each region and the fraud risk level of each community are obtained respectively;

[0025] Obtain the credit fraud score of the user to be evaluated based on the fraud risk level of each region and each community.

[0026] In combination with the first aspect, in one implementation, obtaining the fraud risk level of each region and the fraud risk level of each community respectively according to the proportion of the number of black samples in each region and the proportion of the number of black behavior synchronized communities in each region specifically includes the following steps:

[0027] According to the proportion of black samples in each area and the proportion of communities with synchronized black behaviors in each area, the fraud risk level of each area and each community is obtained by using the degree of improvement as the dividing interval.

[0028] In combination with the first aspect, in one implementation, obtaining the credit fraud score of the user to be evaluated according to the fraud risk level of each region and the fraud risk level of each community specifically includes the following steps:

[0029] The credit fraud score of the user to be evaluated is obtained based on the fraud risk level of each region, the fraud risk level of each community, and the comparison relationship between the regional fraud risk level, the community fraud risk level and the user's credit fraud score.

[0030] In a second aspect, the present application provides a user credit fraud risk assessment system based on LBS data, comprising:

[0031] The credit history information acquisition module is used to obtain the credit application history information within the credit business scope, including the user's credit application time and the user's credit application LBS data;

[0032] An area code acquisition module, which is in communication with the credit history information acquisition module and is used to encode the area information in the LBS data of the user's credit application, and obtain all area codes within the credit business scope;

[0033] A community number acquisition module, which is in communication with the credit history information acquisition module and the area code acquisition module, and is used to acquire all community numbers within the credit business scope according to the user's credit application time and area code;

[0034] A module for acquiring the proportion of black samples and black communities is connected to the credit history information acquisition module, the area code acquisition module, and the community number acquisition module, and is used to obtain the proportion of black samples in each area and the proportion of black behavior synchronization communities in each area based on all area codes and community numbers and historical credit application information acquired within the credit business scope;

[0035] The credit fraud score acquisition module is in communication connection with the black sample and black community proportion acquisition module, and is used to obtain the credit fraud score of the user to be evaluated according to the proportion of black samples in each area and the proportion of black behavior synchronous communities in each area.

[0036] In conjunction with the second aspect, in one implementation, the credit fraud score acquisition module includes:

[0037] A fraud risk level acquisition unit for each region and each community, used to respectively acquire the fraud risk level of each region and the fraud risk level of each community according to the proportion of the number of black samples in each region and the proportion of the number of communities with synchronized black behaviors in each region;

[0038] The user fraud risk assessment unit is in communication connection with the fraud risk level acquisition units for each region and each community, and is used to acquire the credit fraud score of the user to be assessed according to the fraud risk level of each region and the fraud risk level of each community.

[0039] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0040] In the credit field, in response to group fraud, intermediary packaging and other behaviors in the user application stage, by obtaining the proportion of black samples in each region and the proportion of black behavior synchronized communities in each region, we can achieve clustered behavior analysis of LBS data in the user application stage, so as to formulate corresponding anti-fraud identification strategies, identify fraudulent users as accurately as possible without affecting the credit application approval rate, which is conducive to the identification of pre-loan application fraud and post-loan risk management of clustered users. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1This is a flowchart of a method for assessing user credit fraud risk based on LBS data in this application;

[0042] Figure 2 This is a functional module block diagram of the user credit fraud risk assessment system based on LBS data in this application. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0045] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0046] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0047] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0048] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0049] First, as Figure 1 As shown, the embodiment of the present application provides a method for assessing user credit fraud risk based on LBS data, which specifically includes the following steps:

[0050] Step S1: Obtain the original information of the user's credit application, including the user's credit application time and the user's credit application LBS data, denoted as C i (t,lat,lng); where: C i represents user i, i represents the user number, t represents the user application time, (lat, lng) represents the LBS data of the credit application user, more specifically, the geographic location information generated by the credit application behavior, lat represents the latitude data, and lng represents the longitude data;

[0051] Step S2: Encode the area information in the LBS data of the user's credit application to obtain all area codes within the credit business scope;

[0052] Step S3: Obtain all community numbers within the credit business scope according to the user's credit application time and area code;

[0053] Step S4: According to all the regional codes and community numbers and historical credit application information obtained within the scope of the credit business, the percentage of black samples in each region and the percentage of communities with synchronized black behaviors in each region are statistically obtained;

[0054] Step S5: Obtain the credit fraud score of the user to be evaluated based on the proportion of the number of black samples in each area and the proportion of the number of black behavior synchronization communities in each area.

[0055] This application analyzes the clustering behavior of LBS data in the user application stage, and obtains the credit fraud score of the user to be evaluated based on the proportion of black samples in each area and the proportion of black behavior synchronized communities in each area. It identifies fraudulent users as accurately as possible without affecting the credit application approval rate, which is conducive to the identification of pre-loan application fraud and post-loan risk management of clustered users.

[0056] In one embodiment, the step S2: encoding the area information in the LBS data of the user's credit application to obtain all area codes within the credit business scope, specifically includes the following steps:

[0057] The area code of each applicant is calculated based on the LBS data of the applicant based on the Google S2 algorithm and recorded as CellID i , indicating the area code of the applicant with user number i.

[0058] This application uses Google S2 to encode longitude and latitude data, which improves the accuracy of regional coding division and provides more levels of choice for use. It can simultaneously meet the grid division accuracy requirements of longitude and latitude data and the use needs of credit business covering a large geographical range.

[0059] In one embodiment, the step S3: obtaining all community numbers within the credit business scope according to the user's credit application time and area code, specifically includes the following steps:

[0060] For users in the same coding area, based on the user's credit application time and time synchronization range (credit application time range) in the credit application history information, a corresponding time synchronization behavior relationship graph is generated; specifically, the time synchronization behavior relationship graph G is formed by taking the same area code and the same behavior within the time interval T as the association relationship;

[0061] The community discovery algorithm (Louvain algorithm) is used to divide the time synchronization behavior relationship graph into communities, and all community numbers within the credit business scope are obtained, which are recorded as com i Represents the community ID of user i.

[0062] In one embodiment, the step S4: according to all the regional codes and community numbers and historical credit application information obtained within the scope of the credit business, statistically obtaining the proportion of black samples in each region and the proportion of communities with black behaviors in each region, specifically includes the following steps:

[0063] Step S41: According to all regional codes within the credit business scope, the percentage of black samples in each region is counted and recorded as CellBlackRate. i Indicates the proportion of black samples in the area where user i is located;

[0064] Step S42: According to the community number within the credit business scope, the proportion of black samples in each community is counted and recorded as comBlackRate, comBlackRate i Indicates the proportion of black samples in the community where user i belongs;

[0065] Step S43: Calculate the proportion of black behavior synchronization communities in each region based on the proportion of black samples in each region and the proportion of black samples in each community.

[0066] This application adds user time synchronization behavior to credit fraud analysis, which can more accurately mine potential fraud risk users associated with black samples.

[0067] In one embodiment, the step S51: calculating and obtaining the proportion of black behavior synchronized communities in each region according to the proportion of black samples in each region and the proportion of black samples in each community, specifically includes the following steps:

[0068] Step S511: Obtain community tags according to the following rules:

[0069] When the proportion of black samples in a community is greater than the proportion of black samples in the overall area where the community is located, it is defined as a black behavior synchronization community, recorded as 1; otherwise, it is marked as a good behavior synchronization community, recorded as 0, as shown in the following formula:

[0070]

[0071] Where comFlag i Indicates whether the community where user i is located is a black behavior synchronization community;

[0072] Step S512: Count the percentage of black behavior synchronization communities in each area, CellBlackComRate, and use CellBlackComRate i It indicates the proportion of black behavior synchronized communities in the area code of user i’s location.

[0073] Based on the historical information of credit applications within the credit business scope, information derivation processing is performed according to step S1, step S2, step S41 and step S512 to obtain credit application derivative information within the credit business scope, which is expressed as follows:

[0074] C i (t,lat,lng,CellID,CellBlackRate,CellBlackComRate), represents the credit application time of user i, the user's latitude data, longitude data, the proportion of black samples in the area where he is located, and the proportion of black behavior synchronized communities in the area.

[0075] In one embodiment, step S5: obtaining the credit fraud score of the user to be evaluated according to the proportion of the number of black samples in each area and the proportion of the number of black behavior synchronization communities in each area, specifically includes the following steps:

[0076] Step S51: Obtain the fraud risk level of each region and the fraud risk level of each community according to the proportion of the number of black samples in each region and the proportion of the number of black behavior synchronous communities in each region;

[0077] Step S52: Obtain the credit fraud score of the user to be evaluated based on the fraud risk level of each region and the fraud risk level of each community.

[0078] In one embodiment, the step S51: obtaining the credit fraud score of the user to be evaluated according to the proportion of the number of black samples in each area and the proportion of the number of black behavior synchronization communities in each area, specifically includes the following steps:

[0079] Step S511: Obtain the fraud risk level of each region and the fraud risk level of each community according to the proportion of the number of black samples in each region and the proportion of the number of black behavior synchronized communities in each region;

[0080] Step S512: Obtain the credit fraud score of the user to be evaluated based on the fraud risk level of each region and the fraud risk level of each community.

[0081] In one embodiment, the step S511: obtaining the fraud risk level of each region and the fraud risk level of each community respectively according to the proportion of the number of black samples in each region and the proportion of the number of black behavior synchronized communities in each region, specifically includes the following steps:

[0082] According to the proportion of black samples in each region and the proportion of black behavior synchronous communities in each region, the fraud risk level of each region and the fraud risk level of each community are obtained with the degree of improvement as the dividing interval. Specifically, according to the proportion of black samples in each region and the proportion of black behavior synchronous communities, the risk level is divided with the degree of improvement as the dividing interval, and it is divided into four levels from low to high: A, B, C, and D; according to the proportion of black behavior synchronous communities in each region, the risk level is divided with the degree of improvement as the dividing interval, and it is divided into four levels from low to high: A, B, C, and D;

[0083] Among them, the risk level division interval-improvement degree of the proportion of black samples in each area is shown in the following formula:

[0084]

[0085] Where LiftBlack i The risk level of the proportion of black samples in the area where user i is located is divided into intervals;

[0086] The risk level of each region is divided into intervals and improvement degrees based on the proportion of black behavior synchronous communities, as shown in the formula:

[0087]

[0088] Where LiftBlackCom i The risk level division interval for the proportion of black behavior synchronous communities in the area where user i is located.

[0089] In one embodiment, step S512: obtaining a credit fraud score of the user to be evaluated according to the fraud risk level of each region and the fraud risk level of each community, specifically includes the following steps:

[0090] According to the fraud risk level of each region, the fraud risk level of each community, and the corresponding relationship between the regional fraud risk level, the community fraud risk level and the user's credit fraud score (as shown in Table 1), the credit fraud score of the user to be evaluated is obtained.

[0091] Table 1 Comparison table of regional fraud risk level, community fraud risk level and user credit fraud score

[0092] A B C D A 1 1 2 3 B 1 2 3 4 C 2 3 4 5 D 3 4 5 5

[0093] In one embodiment, the step S5: after obtaining the credit fraud score of the user to be evaluated according to the proportion of the number of black samples in each area and the proportion of the number of black behavior synchronized communities in each area, further includes the following steps:

[0094] Based on the risk level of all regional codes within the scope of credit business and the fraud score of users, we adopt a step-by-step hierarchical management for applicants and conduct credit approval according to different approval strategies. We divide users into three risk groups: low, medium, and high according to their fraud scores (the specific division method is shown in Table 2), and conduct secondary division based on the risk grid level. We use LBS data to assist in the identification of fraud risks, and identify fraud risk applications as accurately as possible while ensuring the stability of the customer's credit application approval rate.

[0095] Table 2 Comparison table of user credit fraud scores and customer group management risk levels

[0096]

[0097] In Table 2, L1 to L5 represent the first to fifth levels, respectively.

[0098] Similarly, the division of low, medium and high customer groups can also be promoted as the corresponding division interval. According to the division results in Table 2 above, combined with the user's fraud score, the credit applications in the region with different fraud risk levels are respectively rejected, checked, concerned and normal approval strategies are adopted to identify fraudulent customers as accurately as possible, while having a small impact on the overall approval rate; specifically, users are divided into high risk (corresponding to the user's fraud score of 5), medium-high risk (corresponding to the user's fraud score of 4), medium risk (corresponding to the user's fraud score of 3), and low risk (corresponding to the user's fraud score of 2 and 1). For high-risk users, the credit application is rejected, for medium-high risk users, the credit application is checked, for medium-risk users, the credit application is concerned, and for low-risk users, the normal credit approval process can be used.

[0099] Second, as Figure 2 As shown, the present application provides a user credit fraud risk assessment system based on LBS data, including: a credit history information acquisition module 100 and

[0100] The regional code acquisition module 200, the community number acquisition module 300, the black sample and black community ratio acquisition module 400 and the credit fraud score acquisition module 500. The credit history information acquisition module 100 is used to obtain the credit application history information within the credit business scope, including the user's credit application time and the user's credit application LBS data; the regional code acquisition module 200 is connected in communication with the credit history information acquisition module 100, and is used to encode the regional information in the acquired user's credit application LBS data to obtain all regional codes within the credit business scope; the community number acquisition module 300 is connected in communication with the credit history information acquisition module 100 and the regional code acquisition module 200, and is used to obtain all community numbers within the credit business scope according to the user's credit application time and regional code; The module 400 for acquiring the proportion of black samples and black communities is connected in communication with the module 100 for acquiring the credit history information, the module 200 for acquiring the area code, and the module 300 for acquiring the community number, and is used to obtain the proportion of black samples in each area and the proportion of communities with synchronized black behaviors in each area based on all area codes and community numbers within the scope of the acquired credit business and historical credit application information; the module 500 for acquiring the proportion of black samples and black communities is connected in communication with the module 400 for acquiring the proportion of black communities, and is used to obtain the credit fraud score of the user to be evaluated based on the proportion of black samples in each area and the proportion of communities with synchronized black behaviors in each area.

[0101] In one embodiment, the credit fraud score acquisition module includes:

[0102] A fraud risk level acquisition unit for each region and each community, used to respectively acquire the fraud risk level of each region and the fraud risk level of each community according to the proportion of the number of black samples in each region and the proportion of the number of communities with synchronized black behaviors in each region;

[0103] The user fraud risk assessment unit is in communication connection with the fraud risk level acquisition units for each region and each community, and is used to acquire the credit fraud score of the user to be assessed according to the fraud risk level of each region and the fraud risk level of each community.

[0104] Among them, the functional implementation of each module in the above-mentioned user credit fraud risk assessment system based on LBS data corresponds to the steps in the above-mentioned user credit fraud risk assessment method embodiment based on LBS data, and its functions and implementation processes will not be repeated here one by one.

[0105] On the third aspect, an embodiment of the present application provides a user credit fraud risk assessment device based on LBS data. The user credit fraud risk assessment device based on LBS data can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0106] The communication interface includes an input / output (I / O) interface, a physical interface, and a logical interface, etc., which are used to interconnect the devices inside the user credit fraud risk assessment device based on LBS data, and an interface used to interconnect the user credit fraud risk assessment device based on LBS data with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, an optical fiber interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0107] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0108] The processor may be a general-purpose processor, which may call the user credit fraud risk assessment program based on LBS data stored in the memory and execute the user credit fraud risk assessment method based on LBS data provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the user credit fraud risk assessment program based on LBS data is called may refer to the various embodiments of the user credit fraud risk assessment method based on LBS data of the present application, which will not be repeated here.

[0109] In a fourth aspect, an embodiment of the present application also provides a readable storage medium.

[0110] The user credit fraud risk assessment program based on LBS data is stored on the readable storage medium of the present application, wherein when the user credit fraud risk assessment program based on LBS data is executed by the processor, the steps of the user credit fraud risk assessment method based on LBS data as described above are implemented.

[0111] Among them, the method implemented when the user credit fraud risk assessment program based on LBS data is executed can refer to the various embodiments of the user credit fraud risk assessment method based on LBS data in this application, and will not be repeated here.

[0112] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0113] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0114] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for assessing user credit fraud risk based on LBS data, characterized in that: The following steps are involved: Obtain credit application history information within the credit business scope, including user credit application time and user credit application LBS data; Encode the regional information in the LBS data of the user's credit application to obtain all regional codes within the credit business scope; According to the user's credit application time and area code, obtain all community numbers within the credit business scope; Based on all the regional codes and community numbers within the scope of the credit business and historical credit application information, the percentage of black samples in each region and the percentage of communities with black behaviors in each region are statistically obtained; The credit fraud score of the user to be evaluated is obtained based on the proportion of black samples in each area and the proportion of black behavior synchronized communities in each area.

2. The user credit fraud risk assessment method based on LBS data as claimed in claim 1, characterized in that: The encoding of the area information in the LBS data of the user's credit application is performed to obtain all area codes within the credit business scope, specifically including the following steps: The area code of each applicant is obtained by calculating based on the LBS data of the applicant using the Google S2 algorithm.

3. The user credit fraud risk assessment method based on LBS data as claimed in claim 1, characterized in that: The method of obtaining all community numbers within the credit business scope according to the user's credit application time and area code specifically includes the following steps: For users in the same coding area, a corresponding time synchronization behavior relationship diagram is generated based on the user's credit application time and time synchronization range in the credit application history information; The community discovery algorithm is used to divide the time synchronization behavior relationship graph into communities and obtain all community numbers within the scope of the credit business.

4. The user credit fraud risk assessment method based on LBS data as claimed in claim 1, characterized in that: The method of obtaining the percentage of black samples in each region and the percentage of black behavior synchronous communities in each region based on all regional codes and community numbers and historical credit application information within the obtained credit business scope specifically includes the following steps: According to all regional codes within the credit business scope, the percentage of black samples in each region is counted; According to the community numbers within the credit business scope, the percentage of black samples in each community is counted; According to the proportion of black samples in each area and the proportion of black samples in each community, the proportion of communities with synchronized black behaviors in each area is calculated.

5. The method for assessing user credit fraud risk based on LBS data as claimed in claim 4, characterized in that: The calculation of the proportion of black sample numbers in each region and the proportion of black sample numbers in each community to obtain the proportion of black behavior synchronized communities in each region specifically includes the following steps: When the proportion of black samples in a community is greater than the proportion of black samples in the overall area where the community is located, the community is judged to be a black behavior synchronization community, otherwise it is judged to be a good behavior synchronization community; Count the percentage of black behavior synchronous communities in each region.

6. The method for assessing user credit fraud risk based on LBS data as claimed in claim 1, characterized in that: The method of obtaining the credit fraud score of the user to be evaluated according to the proportion of the number of black samples in each region and the proportion of the number of black behavior synchronized communities in each region specifically includes the following steps: According to the proportion of black samples in each region and the proportion of black behavior synchronous communities in each region, the fraud risk level of each region and the fraud risk level of each community are obtained respectively; Obtain the credit fraud score of the user to be evaluated based on the fraud risk level of each region and each community.

7. The method for assessing user credit fraud risk based on LBS data as claimed in claim 6, characterized in that: The method of obtaining the fraud risk level of each region and the fraud risk level of each community respectively according to the proportion of the number of black samples in each region and the proportion of the number of communities with synchronized black behaviors in each region specifically includes the following steps: According to the proportion of black samples in each area and the proportion of communities with synchronized black behaviors in each area, the fraud risk level of each area and each community is obtained by using the degree of improvement as the dividing interval.

8. The method for assessing user credit fraud risk based on LBS data as claimed in claim 6, characterized in that: The step of obtaining the credit fraud score of the user to be evaluated according to the fraud risk level of each region and the fraud risk level of each community specifically includes the following steps: The credit fraud score of the user to be evaluated is obtained based on the fraud risk level of each region, the fraud risk level of each community, the black sample risk level in the region, the fraud risk level of each community, and the credit fraud score of users in the region.

9. A user credit fraud risk assessment system based on LBS data, characterized in that: include: A credit history information acquisition module is used to acquire credit application history information within the credit business scope, including user credit application time and user credit application LBS data; An area code acquisition module, which is in communication with the credit history information acquisition module and is used to encode the area information in the LBS data of the user's credit application, and obtain all area codes within the credit business scope; A community number acquisition module, which is in communication with the credit history information acquisition module and the area code acquisition module, and is used to acquire all community numbers within the credit business scope according to the user's credit application time and area code; A module for acquiring the proportion of black samples and black communities is connected to the credit history information acquisition module, the area code acquisition module, and the community number acquisition module, and is used to obtain the proportion of black samples in each area and the proportion of black behavior synchronization communities in each area based on all area codes and community numbers and historical credit application information acquired within the credit business scope; The credit fraud score acquisition module is in communication connection with the black sample and black community proportion acquisition module, and is used to obtain the credit fraud score of the user to be evaluated according to the proportion of black samples in each area and the proportion of black behavior synchronous communities in each area.

10. The user credit fraud risk assessment system based on LBS data as claimed in claim 9, characterized in that: The credit fraud score acquisition module includes: A fraud risk level acquisition unit for each region and each community, used to respectively acquire the fraud risk level of each region and the fraud risk level of each community according to the proportion of the number of black samples in each region and the proportion of the number of communities with synchronized black behaviors in each region; The user fraud risk assessment unit is in communication connection with the fraud risk level acquisition units for each region and each community, and is used to acquire the credit fraud score of the user to be assessed according to the fraud risk level of each region and the fraud risk level of each community.

Images