CN110796542A

CN110796542A - Financial risk control method, financial risk control device and electronic equipment

Info

Publication number: CN110796542A
Application number: CN201910915406.5A
Authority: CN
Inventors: 张彤彤; 苏绥绥; 常富洋
Original assignee: Beijing Qilu Information Technology Co Ltd
Current assignee: Beijing Qilu Information Technology Co Ltd
Priority date: 2019-09-26
Filing date: 2019-09-26
Publication date: 2020-02-14

Abstract

The invention provides a financial risk control method, a financial risk control device and electronic equipment. The financial risk control method comprises the following steps: obtaining APP downloading sequence information and financial behavior information of a historical user; vectorizing each APP text information in the APP downloading sequence information of the historical user to generate APP downloading sequence vector data; creating a user risk control model, and training the user risk control model by using the APP download sequence vector data and financial behavior information of historical users; obtaining APP downloading sequence information of a target user, generating target APP downloading sequence vector data, and calculating a financial risk prediction value of the target user by using the user risk control model.

Description

Financial risk control method, financial risk control device and electronic equipment

Technical Field

The invention relates to the field of computer information processing, in particular to a financial risk control method based on a user APP download sequence, a financial risk control device, electronic equipment and a computer readable medium.

Background

Risk control (wind control for short) refers to the risk manager taking various measures and methods to eliminate or reduce the various possibilities of occurrence of a risk event, or the risk controller reducing the losses caused when a risk event occurs. The risk control is generally applied to the financial industry, such as risk control on company transactions, merchant transactions or personal transactions and the like.

With the development of economy, various merchants are increasing, and therefore the wind control demand for the merchants is also increasing. Different wind control rules are defined aiming at different merchants, when the merchants trade, the wind control system executes risk check on the trade of the merchants, identifies risk events and processes the risk events through wind control measures.

In the related art, an IP wind control system is adopted to perform wind control measures on an abnormal IP. However, IP wind control systems on the market generally have the problems of extremely high false killing rate, insufficient dimensionality of IP images, low actual reference value, lack of autonomous learning function and business linkage, low maintainability and expansibility, high IP image library collection cost, uneven quality and the like.

In addition, in the related technology, a wind control method based on user login behavior analysis is disclosed, and a risk early warning value is obtained by establishing and fusing four models of user key risk identification, user login risk identification, password retry risk identification and equipment source risk identification through user login behaviors.

In summary, there is still much room for improvement in internet financial wind control, and therefore, there is a need for a more accurate wind control method.

Disclosure of Invention

In order to solve the above problems, the present invention provides a financial risk control method based on a user APP download sequence, including: obtaining APP downloading sequence information and financial behavior information of a historical user; vectorizing each APP text information in the APP downloading sequence information of the historical user to generate APP downloading sequence vector data; creating a user risk control model, and training the user risk control model by using the APP download sequence vector data and financial behavior information of historical users; obtaining APP downloading sequence information of a target user, generating target APP downloading sequence vector data, and calculating a financial risk prediction value of the target user by using the user risk control model.

Preferably, the financial behavior information includes at least one of credit information, move information, quota information, overdue information and default information.

Preferably, the financial risk prediction value comprises an overdue probability or a default probability.

Preferably, the method further comprises the following steps: and determining the risk level of the target user for the financial product according to the financial risk predicted value.

Preferably, the APP text information includes an APP name and/or an APP profile.

Preferably, the APP download sequence information is APP download sequence information filtered by a first data filtering rule.

Preferably, the first data screening rule is to screen APP download sequence information by a specific time, region or application scenario.

In addition, the present invention also provides a financial risk control device, comprising: the data acquisition module is used for acquiring APP downloading sequence information and financial behavior information of a historical user; the data conversion module is used for vectorizing each APP text information in the APP downloading sequence information of the historical user to generate APP downloading sequence vector data; the training module is used for training a user risk control model by using APP download sequence vector data and financial behavior information of the historical user; and the prediction module is used for acquiring APP download list information of a target user, generating target APP download sequence vector data, and calculating a financial risk prediction value of the target user by using the user risk control model.

Preferably, the method further comprises the following steps: and the risk grade determining module is used for determining the risk grade of the target user for the financial product according to the financial risk predicted value.

In addition, the present invention also provides an electronic device, wherein the electronic device includes: a processor; and a memory storing computer executable instructions that, when executed, cause the processor to perform the financial risk control method of the present invention.

Further, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs which, when executed by a processor, implement the financial risk control method of the present invention.

Advantageous effects

Compared with the prior art, the wind control method provided by the invention has the advantages that the user risk control model is established based on the relation between the APP download sequence vector data in the APP download sequence of the user and the financial behaviors of the user, the APP download sequence vector data of the target user to be detected is input, the financial risk predicted value of the target user is obtained, and the accuracy of the predicted value is improved.

Drawings

In order to make the technical problems solved by the present invention, the technical means adopted and the technical effects obtained more clear, the following will describe in detail the embodiments of the present invention with reference to the accompanying drawings. It should be noted, however, that the drawings described below are only illustrations of exemplary embodiments of the invention, from which other embodiments can be derived by those skilled in the art without inventive faculty.

Fig. 1 is a flowchart of an example of a method for controlling a wind based on a user APP download sequence according to the present invention.

Fig. 2 is a schematic diagram of an example of APP text information of embodiment 1 of the present invention.

Fig. 3 is a schematic diagram of an example of APP text information vectorization of embodiment 1 of the present invention.

Fig. 4 is a flowchart of another example of a method for controlling wind based on a user APP download sequence according to embodiment 1 of the present invention.

Fig. 5 is a schematic diagram of an example of a financial risk control apparatus of embodiment 2 of the present invention.

Fig. 6 is a schematic diagram of another example of the financial risk control apparatus of embodiment 2 of the present invention.

Fig. 7 is a block diagram of an exemplary embodiment of an electronic device according to the present invention.

Fig. 8 is a block diagram of an exemplary embodiment of a computer-readable medium according to the present invention.

Detailed Description

Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. The exemplary embodiments, however, may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art. The same reference numerals denote the same or similar elements, components, or parts in the drawings, and thus their repetitive description will be omitted.

Features, structures, characteristics or other details described in a particular embodiment do not preclude the fact that the features, structures, characteristics or other details may be combined in a suitable manner in one or more other embodiments in accordance with the technical idea of the invention.

In describing particular embodiments, the present invention has been described with reference to features, structures, characteristics or other details that are within the purview of one skilled in the art to provide a thorough understanding of the embodiments. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific features, structures, characteristics, or other details.

The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.

It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, components, or sections, these terms should not be construed as limiting. These phrases are used to distinguish one from another. For example, a first device may also be referred to as a second device without departing from the spirit of the present invention.

The term "and/or" and/or "includes any and all combinations of one or more of the associated listed items.

Example 1

In the following, the method for controlling the wind based on the user APP download sequence according to the present invention will be described with reference to fig. 1 to 4.

Fig. 1 is a flowchart of a wind control method based on a user APP download sequence according to the present invention. As shown in fig. 1, a method for controlling wind based on a user APP download sequence includes the following steps.

In step S201, APP download sequence information and financial behavior information of a history user are acquired.

Specifically, each APP text information in the APP download sequence information of the historical user is vectorized, where the APP text information is, for example, an APP name and/or an APP abstract, and in this embodiment, the wind control method of the present invention is described by taking the APP name as an example, specifically referring to fig. 2 and fig. 3.

Further, the financial behavior information comprises at least one of credit information, dynamic information, quota information, overdue information and default information. In this embodiment, the financial behavior information is overdue information, and the overdue information is used as the training data of the output layer.

In step S202, vectorizing each APP text information in the APP download sequence information of the historical user to generate APP download sequence vector data.

For example, from a mass of historical user APP download sequence information, an APP download sequence table is screened by using a first data screening rule, where the first data screening rule is a specific time, region, or application scene, and further, the specific time is one day, three days, one week, two weeks, three weeks, one month, and the like. In this embodiment, a segment of APP download sequence information downloaded within two weeks is screened, where the segment of APP download sequence information includes 100 APP names, specifically referring to fig. 2.

Further, as shown in fig. 3, the 100 APP names are numbered sequentially based on the downloading order (1, 2, 3, … N, where N is 100), and the 100 APP names are converted into 300-dimensional vector data (i.e., Word vector) by, for example, Word2-vector, etc., and the Word2-vector converts the APP names into 300-dimensional Word vector by, for example, CBOW (surrounding Word pre-estimation center Word) or Skip-Gram (center Word pre-estimation surrounding Word). It should be noted that the method for converting text information into vector data is not limited to word2-vector, but may also be a word set model, a word generation model, an n-gram, a TF-IDF; the 300-dimensional vector data may be 120-dimensional, 200-dimensional, 400-dimensional, etc., and the above description is only for illustration and should not be construed as limiting the present invention.

In addition, the 300-dimensional vector data is further processed into APP download sequence vector data of historical users. Specifically, summing, averaging, and calculating variance are performed on vector data with a 300-dimensional horizontal direction and vector data with a sequence label corresponding to the APP name in a longitudinal direction to obtain APP download sequence vector data of the processed historical user, and the APP download sequence vector data is used as training data of an input layer.

Next, step S203 will be described. In step S203, a user risk control model is created by a Deep neural network DNN (Deep neural network, DNN).

To solve the nonlinear separable problem, a multi-layer functional neuron, i.e., a deep neural network DNN, may be used, wherein the deep neural network DNN specifically includes an input layer, a hidden layer, and an output layer, and both the hidden layer and the output layer neurons are functional neurons that possess activation functions.

In the invention, the created user risk control model is trained by using APP download sequence vector data and overdue information of historical users as training data, wherein the APP download sequence vector data of the historical users are used as the characteristics of an input layer, the overdue information of the historical users is used as the characteristics of an output layer, a deep neural network is trained by using, for example, a Back Propagation (BP) algorithm, and the connection weight between neurons and the threshold value of each functional neuron are adjusted according to the training data, so that the classification of the overdue probability (namely, financial risk) of the historical users is realized based on the vector data of the input layer and the overdue information of the historical users.

Next, a user risk control model in the wind control method of the present invention will be specifically described.

First, input training set

And learning rate is provided for input layer neurons, wherein x is the obtained APP download sequence vector data of the historical user, and y is the overdue probability of the historical user; the learning rate can be given by considering by those skilled in the art, or based on a gradient descent (gradient) strategy, each parameter is adjusted in a target negative gradient direction, and the learning rate is given for errors; assuming that the hidden layer and the output layer both use Sigmoid function, the network position (x) can be calculated_k,y_k) The mean square error of (c).

Specifically, all connection rights and thresholds in the network are initialized randomly within a range of (0, 1), sequence vector data (namely current parameters) are downloaded according to APP of a historical user, and then signals are forwarded layer by layer until an output result is generated; and then calculating the error of the output layer, reversely transmitting the error to a hidden layer neuron, adjusting the connection weight and the threshold according to the error of the hidden layer neuron, and finally outputting the neural network after parameter adjustment. The user risk control model of the invention predicts the financial risk of the target user based on the neural network after parameter adjustment.

It should be noted that the above is only for illustration and should not be construed as limiting the present invention, and an RBF network, an SOM network, a cascade correlation network, etc. may be used in addition to the deep neural network DNN.

In addition, in this embodiment, data preprocessing is further performed on APP download lists of different history users in the above time period, where the data preprocessing includes transition, smoothing, and padding. In addition, the method also comprises the step of capturing the update times of the APP in time, so that the obtained APP data is more accurate.

In addition, APP category information is obtained, for example, by crawling or the like, specifically, APP categories include loan, fitness, consumption, food, live broadcast, and the like, see fig. specifically.

Next, step S204 will be described. Step S204 is a step of predicting the financial risk of the target user. Specifically, the financial risk prediction value of the target user is calculated by using the created user risk control model, wherein the financial risk prediction value comprises an overdue probability or a default probability, and in the embodiment, the overdue probability. Or determining the risk level of the target user for the financial product based on the overdue probability, without being limited thereto.

In this embodiment, good and bad samples are defined, and the label is 0 and 1, where 1 represents a sample with a probability of overdue by the user being Y or more, and 0 represents a sample with a probability of overdue by the user being less than Y. Generally, the lower the probability that a user is overdue, the better the loan is to recover principal, the more efficient the use of funds, the lower the risk level of the property, and vice versa.

Specifically, the determination of the Y value is determined, for example, by human determination by a person skilled in the art, or calculated by using a bad mark rate (where the bad mark rate is mark number/total mark number that is more than 30 days past). In addition, based on a gradient descent (gradient) strategy, each parameter can be adjusted in a target negative gradient direction, and an optimal solution (Y value) can be calculated for an error and a given learning rate.

In the present embodiment, Y is, for example, 3.25%. Further, 1 represents a sample in which the probability of the user being overdue is 3.25% or more, and 0 represents a sample in which the probability of the user being overdue is less than 3.25%.

Next, APP download sequence information of the target user is obtained, and for the obtained APP download sequence information of the target user, the APP download sequence table is filtered by using, for example, a second data filtering rule, in this embodiment, the second data filtering rule is the same as the first data filtering rule, but may also be different. Without being limited thereto, in other embodiments, the data screening process may not be included.

Preferably, the target APP download sequence vector data is generated by, for example, word2-vector, etc.

And inputting the generated target APP download sequence vector data into the created user risk control model, so as to obtain a risk prediction value of the target user.

It should be noted that the above-mentioned embodiments are only preferred embodiments, and should not be construed as limiting the present invention. In other embodiments, the user risk control model may also be used to calculate the risk level of the user, or as a prediction module in other risk prediction models, and so on.

Those skilled in the art will appreciate that all or part of the steps to implement the above-described embodiments are implemented as programs (computer programs) executed by a computer data processing apparatus. When the computer program is executed, the method provided by the invention can be realized. Furthermore, the computer program may be stored in a computer readable storage medium, which may be a readable storage medium such as a magnetic disk, an optical disk, a ROM, a RAM, or a storage array composed of a plurality of storage media, such as a magnetic disk or a magnetic tape storage array. The storage medium is not limited to centralized storage, but may be distributed storage, such as cloud storage based on cloud computing.

Example 2

Embodiments of the apparatus of the present invention are described below, which may be used to perform method embodiments of the present invention. The details described in the device embodiments of the invention should be regarded as complementary to the above-described method embodiments; reference is made to the above-described method embodiments for details not disclosed in the apparatus embodiments of the invention.

Referring to fig. 5 and 6, the present invention also provides a financial risk control apparatus 500, which includes: a data obtaining module 501, configured to obtain APP download sequence information and financial behavior information of a historical user; a data conversion module 502, configured to vectorize each APP text information in the APP download sequence information of the historical user, to generate APP download sequence vector data; a training module 503, configured to train a user risk control model by using APP download sequence vector data and financial behavior information of the historical user; the prediction module 504 is configured to obtain APP download list information of a target user, generate target APP download sequence vector data, and calculate a financial risk prediction value of the target user using the user risk control model.

Preferably, the method further comprises the following steps: a risk level determining module 601, configured to determine a risk level of the target user for the financial product according to the predicted financial risk value, specifically referring to fig. 6.

In embodiment 2, the same portions as those in embodiment 1 are not described.

Those skilled in the art will appreciate that the modules in the above-described embodiments of the apparatus may be distributed as described in the apparatus, and may be correspondingly modified and distributed in one or more apparatuses other than the above-described embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.

Example 3

In the following, embodiments of the electronic device of the present invention are described, which may be regarded as specific physical implementations for the above-described embodiments of the method and apparatus of the present invention. Details described in the embodiments of the electronic device of the invention should be considered supplementary to the embodiments of the method or apparatus described above; for details which are not disclosed in embodiments of the electronic device of the invention, reference may be made to the above-described embodiments of the method or the apparatus.

Fig. 7 is a block diagram of an exemplary embodiment of an electronic device according to the present invention. An electronic apparatus 200 according to this embodiment of the present invention is described below with reference to fig. 7. The electronic device 200 shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 7, the electronic device 200 is embodied in the form of a general purpose computing device. The components of the electronic device 200 may include, but are not limited to: at least one processing unit 210, at least one memory unit 220, a bus 230 connecting different system components (including the memory unit 220 and the processing unit 210), a display unit 240, and the like.

Wherein the storage unit stores program code executable by the processing unit 210 to cause the processing unit 210 to perform the steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of the present specification. For example, the processing unit 210 may perform the steps as shown in fig. 1.

The memory unit 220 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)2201 and/or a cache memory unit 2202, and may further include a read only memory unit (ROM) 2203.

The storage unit 220 may also include a program/utility 2204 having a set (at least one) of program modules 2205, such program modules 2205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 230 may be one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 200 may also communicate with one or more external devices 300 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 200, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 200 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 250. Also, the electronic device 200 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 260. The network adapter 260 may communicate with other modules of the electronic device 200 via the bus 230. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments of the present invention described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to make a computing device (which can be a personal computer, a server, or a network device, etc.) execute the above-mentioned method according to the present invention. The computer program, when executed by a data processing apparatus, enables the computer readable medium to implement the above-described method of the invention, namely: and training the created user risk control model by using APP download sequence vector data and overdue information of the historical user as training data, and calculating the financial risk prediction value of the target user by using the created user risk control model.

As shown in fig. 8, the computer program may be stored on one or more computer readable media. The computer readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

In summary, the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components in embodiments in accordance with the invention may be implemented in practice using a general purpose data processing device such as a microprocessor or a Digital Signal Processor (DSP). The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

While the foregoing embodiments have described the objects, aspects and advantages of the present invention in further detail, it should be understood that the present invention is not inherently related to any particular computer, virtual machine or electronic device, and various general-purpose machines may be used to implement the present invention. The invention is not to be considered as limited to the specific embodiments thereof, but is to be understood as being modified in all respects, all changes and equivalents that come within the spirit and scope of the invention.

Claims

1. A financial risk control method based on a user APP download sequence is characterized by comprising the following steps:

obtaining APP downloading sequence information and financial behavior information of a historical user;

vectorizing each APP text information in the APP downloading sequence information of the historical user to generate APP downloading sequence vector data;

creating a user risk control model, and training the user risk control model by using the APP download sequence vector data and financial behavior information of historical users;

obtaining APP downloading sequence information of a target user, generating target APP downloading sequence vector data, and calculating a financial risk prediction value of the target user by using the user risk control model.

2. The financial risk control method of claim 1, wherein the financial behavior information includes at least one of credit information, move information, credit information, overdue information, default information.

3. The method of any of claims 1-2, wherein the financial risk prediction value comprises an overdue probability or a default probability.

4. The financial risk control method of any one of claims 1-3, further comprising: and determining the risk level of the target user for the financial product according to the financial risk predicted value.

5. The financial risk control method of any of claims 1-4, wherein the APP text information includes an APP name and/or an APP profile.

6. The financial risk control method according to any one of claims 1-5, wherein the APP download sequence information is APP download sequence information filtered by a first data filtering rule.

7. The financial risk control method according to any one of claims 1-6, wherein the first data filtering rule is to filter APP download sequence information by a specific time, region or application scenario.

8. A financial risk control device, comprising:

the data acquisition module is used for acquiring APP downloading sequence information and financial behavior information of a historical user;

the data conversion module is used for vectorizing each APP text information in the APP downloading sequence information of the historical user to generate APP downloading sequence vector data;

the training module is used for training a user risk control model by using APP download sequence vector data and financial behavior information of the historical user;

and the prediction module is used for acquiring APP download list information of a target user, generating target APP download sequence vector data, and calculating a financial risk prediction value of the target user by using the user risk control model.

9. An electronic device, wherein the electronic device comprises:

a processor; and the number of the first and second groups,

a memory storing computer-executable instructions that, when executed, cause the processor to perform the financial risk control method of any one of claims 1-7.

10. A computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement the financial risk control method of any of claims 1-7.