CN112419050B - Credit evaluation method and device based on telephone communication network and social behavior - Google Patents
Credit evaluation method and device based on telephone communication network and social behavior Download PDFInfo
- Publication number
- CN112419050B CN112419050B CN202011546995.3A CN202011546995A CN112419050B CN 112419050 B CN112419050 B CN 112419050B CN 202011546995 A CN202011546995 A CN 202011546995A CN 112419050 B CN112419050 B CN 112419050B
- Authority
- CN
- China
- Prior art keywords
- income
- data
- communication
- user
- calculating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Abstract
The embodiment of the invention provides a credit assessment method and a device based on a telephone communication network and social behaviors, wherein the method comprises the following steps: acquiring communication information of a user, and establishing a communication adjacent matrix according to the communication information; acquiring a communication object in the communication information, acquiring default customers in the communication object, and calculating the diffusion energy of the default customers through a preset diffusion activation model; calculating a risk exposure value of the communication object through diffusion energy by combining the adjacency matrix; acquiring social data of a user, inputting the social data and the risk exposure value into a preset random forest measurement model as profit characteristics, and calculating the profit data of the profit characteristics; and judging whether the corresponding user is a default user or a conservative user and the individual profit condition of the corresponding user according to the profit data. By adopting the method, the credit evaluation can be carried out on the client according to the related consumption and social behaviors, so that the evaluation result is more comprehensive, and the accuracy of the credit evaluation is also improved.
Description
Technical Field
The invention relates to the technical field of credit assessment, in particular to a credit assessment method and device based on a telephone communication network and social behaviors.
Background
With the increasing popularity of credit, people can choose various loan methods to solve when facing the situation of insufficient funds. In the existing loan service, the credit of the user is generally evaluated according to the acquired personal data of the user, previous loan records, bank flow and other information, so that the user is issued with a loan according to the credit of the user and the loan amount applied by the user.
However, with the advent of the big data age, the credit evaluation method is not comprehensive enough and not accurate enough, for example, the credit relationship between the client and the client, and the social behavior of the client itself can also become the "guarantor" of the client, and the existing user credit evaluation method does not utilize the above evaluation factors.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a credit evaluation method and device based on a telephone communication network and social behaviors.
The embodiment of the invention provides a credit assessment method based on a telephone communication network and social behaviors, which comprises the following steps:
acquiring communication information of a user, and establishing a communication adjacent matrix according to the communication information;
acquiring a communication object in the communication information, acquiring default customers in the communication object, and calculating the diffusion energy of the default customers through a preset diffusion activation model;
Calculating a risk exposure value of the communication object through the diffusion energy by combining the adjacency matrix;
acquiring social data of the user, inputting the social data and the risk exposure value into a preset random forest measurement model as benefit characteristics, and calculating the benefit data of the benefit characteristics;
and judging that the corresponding user is a default user or a conservative user and the individual profit condition of the corresponding user according to the profit data.
In one embodiment, the method further comprises:
acquiring historical income characteristics in a historical sample, and establishing a test data set;
training feature data corresponding to the historical income features through the random forest measurement model to obtain a prediction tree corresponding to a historical sample;
establishing a confusion matrix, and calculating the benefit of the prediction tree;
calculating the average reduction benefit of the historical benefit characteristics in the test data set according to the benefit of the prediction tree;
screening the average reduction income of the historical income characteristics to obtain income data corresponding to each historical income characteristic;
and acquiring a preset EMP formula, and calculating to obtain the income data of the income characteristics by combining the income data and the income characteristics corresponding to the historical income characteristics.
In one embodiment, the communication information includes:
communication object, communication time length, communication initiator and communication object type.
In one embodiment, the method further comprises:
and determining the adjacent edge of the adjacent matrix through the communication object, expressing the weight of the adjacent edge through the communication time length, determining the direction of the adjacent edge through the communication initiator, and setting the label of the corresponding node of the communication object through the type of the communication object.
In one embodiment, the social data includes:
personal consumption data, personal income data, personal payment data and personal payment data of the communication object.
In one embodiment, the method further comprises:
and calculating the total income of the communication object, and adjusting the parameters of the random forest measuring model according to the individual income condition and the total income.
The embodiment of the invention provides a credit evaluation device based on a telephone communication network and social behaviors, which comprises:
the first acquisition module is used for acquiring communication information of a user and determining a communication adjacent matrix according to the communication information;
the second acquisition module is used for acquiring a communication object in the communication information, acquiring default customers in the communication object and calculating the diffusion energy of the default customers through a preset diffusion activation model;
The calculation module is used for combining the adjacency matrix and calculating a risk exposure value of the communication object through the diffusion energy;
the third acquisition module is used for acquiring social data of the user, inputting the social data and the risk exposure value into a preset random forest measurement model as profit characteristics, and calculating the profit data of the profit characteristics;
and the judging module is used for judging that the corresponding user is a default user or a conservative user and the individual profit condition of the corresponding user according to the profit data.
In one embodiment, the apparatus further comprises:
the fourth acquisition module is used for acquiring historical income characteristics in the historical samples and establishing a test data set;
the training module is used for training the feature data corresponding to the historical income features through the random forest measurement model to obtain a prediction tree corresponding to a historical sample;
the building module is used for building a confusion matrix and calculating the income of the prediction tree;
the second calculation module is used for calculating the average reduction benefit of the historical benefit characteristics in the test data set according to the benefit of the prediction tree;
the screening module is used for screening the average reduction income of the historical income characteristics to obtain income data corresponding to each historical income characteristic;
And the third calculation module is used for acquiring a preset EMP formula, and calculating to obtain the income data of the income characteristics by combining the income data and the income characteristics corresponding to the historical income characteristics.
The embodiment of the invention provides electronic equipment, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the steps of the credit evaluation method based on the telephone communication network and the social behaviors.
Embodiments of the present invention provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the above-mentioned credit assessment method based on a telephone communication network and social behaviors.
According to the credit evaluation method and device based on the telephone communication network and the social behavior, the communication information of the user is obtained, and a communication adjacent matrix is established according to the communication information; acquiring a communication object in the communication information, acquiring default customers in the communication object, and calculating the diffusion energy of the default customers through a preset diffusion activation model; calculating a risk exposure value of the communication object through diffusion energy by combining the adjacency matrix; acquiring social data of a user, inputting the social data and the risk exposure value into a preset random forest measurement model as profit characteristics, and calculating the profit data of the profit characteristics; and judging whether the corresponding user is a default user or a conservative user and the individual profit condition of the corresponding user according to the profit data. Therefore, the credit assessment is carried out on the client by combining the related consumption and social behaviors, so that the assessment result is more comprehensive, and the accuracy of the credit assessment is also improved.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the embodiments or technical solutions in the prior art are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart of a method for credit assessment based on telephony and social activities according to an embodiment of the present invention;
FIG. 2 is a block diagram of a credit evaluation device based on a phone communication network and social activities according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a credit evaluation method based on a telephone communication network and social behaviors provided in an embodiment of the present invention, and as shown in fig. 1, an embodiment of the present invention provides a credit evaluation method based on a telephone communication network and social behaviors, including:
and step S101, communication information of a user is obtained, and a communication adjacent matrix is established according to the communication information.
Specifically, communication information in the user call information table is obtained, where the communication information includes a communication object, a communication duration, a communication initiator, a communication object type (that is, the communication object is a default user or a conservative user), and the like, then a corresponding communication adjacency matrix is established according to the communication information, that is, all users in the call information table are abstracted into corresponding nodes, then an adjacent side of the adjacency matrix is determined by the communication object, a weight of the adjacent side is represented by the communication duration, a direction of the adjacent side is determined by the communication initiator, and a label of the corresponding node of the communication object is set by the communication object type, and a specific establishment process may be: if the user has a relationship between the call information tables, the connection of the edges exists between the two, and the connection is drawn asAdjacent to the matrix. Representing weights of edges by durations of calls between each other Wherein. The matrix can be divided into directed edges by the behaviors of dialing and dialed, and dialing is carried outIndicating out-degree, dialed to indicate in-degree. Node pointSet of neighbor nodes of the first order. And labeling the nodes according to individual repayment conditions, and dividing the nodes into default and reservation types.
Step S102, a communication object in the communication information is obtained, default customers in the communication object are obtained, and diffusion energy of the default customers is calculated through a preset diffusion activation model.
Specifically, default customers of the communication object in the communication information are obtained, and the diffusion energy of the default customers is calculated according to a preset diffusion activation model, and since each default customer carries energy and can diffuse the node energy to other neighbor nodes, a diffusion activation model (SPA) can be utilized. Assume a set of active nodes (default customers) asCarried with energy of. After k iterations, the node energy of the active node d part is diffused to its neighbor nodes, and this energy is defined as transfer energy, which can be expressed as:
when no new neighbor node is affected and the energy change is less than the threshold, the activation model stops, thus gaining the energy of the offending customer's diffusion in the adjacency matrix.
And step S103, combining the adjacency matrix, and calculating the risk exposure value of the communication object through the diffusion energy.
In particular, communication is calculated by diffusion energyThe risk exposure value of the object may be obtained by using a modified PageRank algorithm, such as assuming that the weight matrix in the network is W, and the risk exposure value of each pointThe damping coefficient is () representing a random probability, and the calculation formula is
And calculating the risk exposure value of each point in the network by using a diffusion activation model (SPA) and a modified PageRank algorithm. In addition, when the energy value of the node is smaller than a set critical value, the node is defined as a low-risk node; when the energy value is higher than a set critical value, a high-risk node is defined.
And S104, acquiring social data of the user, inputting the social data and the risk exposure value into a preset random forest measurement model as profit characteristics, and calculating the profit data of the profit characteristics.
Specifically, social data of a user are obtained, wherein the social data can comprise personal consumption data, personal income data, personal payment data and personal payment data of a communication object, the main reference objects are the personal payment data of the user and the personal payment data of the communication object of the user, then the social data and the calculated risk exposure value of each node are used as income characteristics and input into a preset random forest measurement model, and income data corresponding to the income characteristics in each node are calculated.
And S105, judging that the corresponding user is a default user or a conservative user and the individual profit condition of the corresponding user according to the profit data.
Specifically, income data in the random forest measurement model is obtained through calculation, the judged limit value is obtained, the data point whether the data point is higher than the limit value is divided into corresponding default users or conservative users, and the individual income condition of each user is calculated when the user is subjected to loan.
The embodiment of the invention provides a credit evaluation method based on a telephone communication network and social behaviors, which comprises the steps of obtaining communication information of a user, and establishing a communication adjacency matrix according to the communication information; acquiring a communication object in communication information, acquiring default customers in the communication object, and calculating the diffusion energy of the default customers through a preset diffusion activation model; calculating a risk exposure value of the communication object through diffusion energy by combining the adjacency matrix; acquiring social data of a user, inputting the social data and the risk exposure value into a preset random forest measurement model as profit characteristics, and calculating the profit data of the profit characteristics; and judging whether the corresponding user is a default user or a conservative user and the individual profit condition of the corresponding user according to the profit data. Therefore, the credit assessment is carried out on the client by combining the related consumption and social behaviors, so that the assessment result is more comprehensive, and the accuracy of the credit assessment is also improved.
On the basis of the above embodiment, the credit evaluation method based on the phone communication network and social behavior further includes:
acquiring historical income characteristics in a historical sample, and establishing a test data set;
training feature data corresponding to the historical income features through the random forest measurement model to obtain a prediction tree corresponding to a historical sample;
establishing a confusion matrix, and calculating the benefit of the prediction tree;
calculating the average reduction benefit of the historical benefit characteristics in the test data set according to the benefit of the prediction tree;
screening the average reduction income of the historical income characteristics to obtain income data corresponding to each historical income characteristic;
and acquiring a preset EMP formula, and calculating to obtain the income data of the income characteristics by combining the income data and the income characteristics corresponding to the historical income characteristics.
In the embodiment of the present invention, the profit data of the profit characteristics are calculated by using the random forest measurement model through the preset steps, and the specific detailed calculation steps may be, for example: suppose a random forest model () With N samplesNumber of m featuresThe method comprises the following steps:
Each feature in the test data set is calculated and the average diminishing returns are calculated. The definition is as follows:. WhereinRepresentation featureBelong to a tree。
S105, the adjusted EMP expected maximum profit evaluation index:
the expression is the average profit for each lender,the probability of a table being a default person (a keeper),a density function representing the accumulated defaults (the coworkers). The optimal function that can be obtained is:
indicating the benefit of correctly identifying the offender, i.e.LGD (loss given default) represents default loss rate, EAD (excess at default) represents the amount of funds for which a default risk may occur, and A represents the amount of loan.Loss representing a misjudged contractor as a default is equivalent to a loan Return On Investment (ROI).Which represents the cost of the operation and,the cost/benefit ratio is expressed in terms of,a joint probability density representing the classification loss with an optimal cutoff value of. When in useTime means that no loss occurs after rejection of a client.
According to the embodiment of the invention, the profit influence generated by each characteristic in each node is calculated through the steps.
On the basis of the above embodiment, the credit evaluation method based on the telephony network and the social behavior further includes:
And calculating the total income of the communication object, and adjusting the parameters of the random forest measuring model according to the individual income condition and the total income.
In the embodiment of the invention, after the individual income condition of the user is calculated, the total income of the communication objects (each node) can be calculated, wherein the calculation method can be used for feeding back the calculation result data to the random forest measurement model through the confusion matrix so as to correspondingly adjust the parameters of the random forest measurement model. Wherein the confusion matrix may be as shown in table 1:
TABLE 1
According to the embodiment of the invention, the parameters of the random forest measurement model are adjusted through the feedback of the income result, so that the parameters of the random forest measurement model are more accurate.
Fig. 2 is a credit evaluation device based on a phone communication network and social behaviors according to an embodiment of the present invention, including: a first obtaining module 201, a second obtaining module 202, a calculating module 203, a third obtaining module 204, and a determining module 205, wherein:
the first obtaining module 201 is configured to obtain communication information of a user, and determine a communication adjacent matrix according to the communication information.
A second obtaining module 202, configured to obtain a communication object in the communication information, obtain a default customer in the communication object, and calculate a diffusion energy of the default customer through a preset diffusion activation model.
And the calculating module 203 is used for combining the adjacency matrix and calculating the risk exposure value of the communication object through the diffusion energy.
And a third obtaining module 204, configured to obtain social data of the user, input the social data and the risk exposure value into a preset random forest measurement model as benefit characteristics, and calculate benefit data of the benefit characteristics.
The determining module 205 is configured to determine, according to the profit data, that the corresponding user is a default user or a conservative user, and an individual profit situation of the corresponding user.
In one embodiment, the apparatus may further comprise:
and the fourth acquisition module is used for acquiring the historical income characteristics in the historical samples and establishing the test data set.
And the training module is used for training the feature data corresponding to the historical income features through the random forest measurement model to obtain a prediction tree corresponding to the historical sample.
And the establishing module is used for establishing a confusion matrix and calculating the income of the prediction tree.
And the second calculation module is used for calculating the average reduction benefit of the historical benefit characteristics in the test data set according to the benefit of the prediction tree.
And the screening module is used for screening the average reduction income of the historical income characteristics to obtain income data corresponding to each historical income characteristic.
And the third calculation module is used for acquiring a preset EMP formula, and calculating to obtain the income data of the income characteristics by combining the income data and the income characteristics corresponding to the historical income characteristics.
In one embodiment, the apparatus may further comprise:
and the fourth calculation module is used for calculating the total income of the communication object and adjusting the parameters of the random forest measurement model according to the individual income condition and the total income.
For specific limitations of the credit evaluation device based on the phone communication network and the social behavior, reference may be made to the above limitations of the credit evaluation method based on the phone communication network and the social behavior, which are not described herein again. The various modules in the above-described credit assessment device based on the telephony network and social behavior may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Fig. 3 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 3: a processor (processor)301, a memory (memory)302, a communication Interface (Communications Interface)303 and a communication bus 304, wherein the processor 301, the memory 302 and the communication Interface 303 complete communication with each other through the communication bus 304. The processor 301 may call logic instructions in the memory 302 to perform the following method: acquiring communication information of a user, and establishing a communication adjacent matrix according to the communication information; acquiring a communication object in the communication information, acquiring default customers in the communication object, and calculating the diffusion energy of the default customers through a preset diffusion activation model; calculating a risk exposure value of the communication object through diffusion energy by combining the adjacency matrix; acquiring social data of a user, inputting the social data and the risk exposure value into a preset random forest measurement model as profit characteristics, and calculating the profit data of the profit characteristics; and judging whether the corresponding user is a default user or a conservative user and the individual profit condition of the corresponding user according to the profit data.
Furthermore, the logic instructions in the memory 302 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the transmission method provided in the foregoing embodiments when executed by a processor, and for example, the method includes: acquiring communication information of a user, and establishing a communication adjacent matrix according to the communication information; acquiring a communication object in the communication information, acquiring default customers in the communication object, and calculating the diffusion energy of the default customers through a preset diffusion activation model; calculating a risk exposure value of the communication object through diffusion energy by combining the adjacency matrix; acquiring social data of a user, inputting the social data and the risk exposure value into a preset random forest measurement model as profit characteristics, and calculating the profit data of the profit characteristics; and judging whether the corresponding user is a default user or a conservative user and the individual profit condition of the corresponding user according to the profit data.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A credit assessment method based on a telephone communication network and social behaviors is characterized by comprising the following steps:
acquiring communication information of a user, and establishing a communication adjacent matrix according to the communication information;
acquiring a communication object in the communication information, acquiring default customers in the communication object, and calculating the diffusion energy of the default customers through a preset diffusion activation model, wherein a calculation formula of the diffusion energy of the default customers comprises:
calculating the risk exposure value of the communication object by combining the adjacency matrix and the diffusion energy, wherein the calculation formula for calculating the risk exposure value of the communication object comprises:
Acquiring social data of the user, inputting the social data and the risk exposure value into a preset random forest measurement model as profit characteristics, and calculating the profit data of the profit characteristics;
judging whether the corresponding user is a default user or a conservative user and the individual profit condition of the corresponding user according to the profit data;
wherein calculating revenue data for the revenue feature comprises:
acquiring historical income characteristics in a historical sample, and establishing a test data set;
training feature data corresponding to the historical income features through the random forest measurement model to obtain a prediction tree corresponding to a historical sample;
establishing a confusion matrix, and calculating the benefit of the prediction tree;
calculating the average reduction benefit of the historical benefit characteristics in the test data set according to the benefit of the prediction tree;
screening the average reduction income of the historical income characteristics to obtain income data corresponding to each historical income characteristic;
and acquiring a preset EMP formula, and calculating to obtain the income data of the income characteristics by combining the income data and the income characteristics corresponding to the historical income characteristics.
2. The method of claim 1, wherein the communication information comprises:
Communication object, communication time length, communication initiator and communication object type.
3. The method of claim 2, wherein the establishing a communication adjacency matrix according to the communication information comprises:
and determining the adjacent edge of the adjacent matrix through the communication object, representing the weight of the adjacent edge through the communication time, determining the direction of the adjacent edge through the communication initiator, and setting the label of the corresponding node of the communication object through the type of the communication object.
4. The method of claim 1, wherein the social data comprises:
personal consumption data, personal income data, personal repayment data and personal repayment data of the communication object.
5. The method of claim 1, wherein after determining the corresponding user as a default user or a conservative user and the individual profit of the corresponding user according to the profit data, the method further comprises:
and calculating the total income of the communication object, and adjusting the parameters of the random forest measuring model according to the individual income condition and the total income.
6. A credit assessment device based on telephony and social activities, the device comprising:
the first acquisition module is used for acquiring communication information of a user and determining a communication adjacent matrix according to the communication information;
a second obtaining module, configured to obtain a communication object in the communication information, obtain a default customer in the communication object, and calculate diffusion energy of the default customer through a preset diffusion activation model, where a calculation formula of the diffusion energy of the default customer includes:
a calculation module, configured to calculate a risk exposure value of the communication object through the diffusion energy in combination with the adjacency matrix, where the calculation formula for calculating the risk exposure value of the communication object includes:
the third acquisition module is used for acquiring social data of the user, inputting the social data and the risk exposure value into a preset random forest measurement model as profit characteristics, and calculating the profit data of the profit characteristics;
the judging module is used for judging whether the corresponding user is a default user or a conservative user and the individual income condition of the corresponding user according to the income data;
The fourth acquisition module is used for acquiring historical income characteristics in the historical samples and establishing a test data set;
the training module is used for training the feature data corresponding to the historical profit features through the random forest measurement model to obtain a prediction tree corresponding to a historical sample;
the building module is used for building a confusion matrix and calculating the benefit of the prediction tree;
the second calculation module is used for calculating the average reduction benefit of the historical benefit characteristics in the test data set according to the benefit of the prediction tree;
the screening module is used for screening the average reduction income of the historical income characteristics to obtain income data corresponding to each historical income characteristic;
and the third calculation module is used for acquiring a preset EMP formula, and calculating to obtain the income data of the income characteristics by combining the income data and the income characteristics corresponding to the historical income characteristics.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method for credit assessment based on telephony networks and social behaviour according to any one of claims 1 to 5.
8. A non-transitory computer readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method for credit assessment based on telephony networks and social behaviors as claimed in any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011546995.3A CN112419050B (en) | 2020-12-24 | 2020-12-24 | Credit evaluation method and device based on telephone communication network and social behavior |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011546995.3A CN112419050B (en) | 2020-12-24 | 2020-12-24 | Credit evaluation method and device based on telephone communication network and social behavior |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112419050A CN112419050A (en) | 2021-02-26 |
CN112419050B true CN112419050B (en) | 2022-05-24 |
Family
ID=74782767
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011546995.3A Active CN112419050B (en) | 2020-12-24 | 2020-12-24 | Credit evaluation method and device based on telephone communication network and social behavior |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112419050B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108629677A (en) * | 2017-03-23 | 2018-10-09 | 上海仟才金融信息服务有限公司 | A kind of credit estimation method based on the social big data of communication |
CN112037009A (en) * | 2020-08-06 | 2020-12-04 | 百维金科(上海)信息科技有限公司 | Risk assessment method for consumption credit scene based on random forest algorithm |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106127363B (en) * | 2016-06-12 | 2022-04-15 | 腾讯科技(深圳)有限公司 | User credit assessment method and device |
CN108734565B (en) * | 2017-04-14 | 2020-11-17 | 腾讯科技(深圳)有限公司 | Credit investigation point real-time adjustment processing method and device and processing server |
US10692058B2 (en) * | 2017-09-06 | 2020-06-23 | Fair Isaac Corporation | Fraud detection by profiling aggregate customer anonymous behavior |
US11288674B2 (en) * | 2018-01-08 | 2022-03-29 | Visa International Service Association | System, method, and computer program product for determining fraud rules |
-
2020
- 2020-12-24 CN CN202011546995.3A patent/CN112419050B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108629677A (en) * | 2017-03-23 | 2018-10-09 | 上海仟才金融信息服务有限公司 | A kind of credit estimation method based on the social big data of communication |
CN112037009A (en) * | 2020-08-06 | 2020-12-04 | 百维金科(上海)信息科技有限公司 | Risk assessment method for consumption credit scene based on random forest algorithm |
Non-Patent Citations (1)
Title |
---|
TWIT:社交网络中局部信任值的双向计算;李凤岐等;《计算机工程与应用》;20160215(第04期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112419050A (en) | 2021-02-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110866767A (en) | Method, device, equipment and medium for predicting satisfaction degree of telecommunication user | |
CN109802915A (en) | A kind of telecommunication fraud detection processing method and device | |
CN113206909A (en) | Crank call interception method and device | |
CN111061948B (en) | User tag recommendation method and device, computer equipment and storage medium | |
CN109360104A (en) | User type division methods, system, computer equipment and storage medium | |
CN115689752A (en) | Method, device and equipment for adjusting wind control rule and storage medium | |
CN111428217A (en) | Method and device for identifying cheat group, electronic equipment and computer readable storage medium | |
CN114782123A (en) | Credit assessment method and system | |
CN111105064A (en) | Method and device for determining suspected information of fraud event | |
CN113570260A (en) | Task allocation method, computer-readable storage medium and electronic device | |
CN112419050B (en) | Credit evaluation method and device based on telephone communication network and social behavior | |
CN109711984B (en) | Pre-loan risk monitoring method and device based on collection urging | |
CN112035570A (en) | Merchant evaluation method and system | |
CN110781410A (en) | Community detection method and device | |
CN111062422A (en) | Method and device for systematic identification of road loan | |
CN110458707B (en) | Behavior evaluation method and device based on classification model and terminal equipment | |
CN113177837A (en) | Loan amount evaluation method, device, equipment and storage medium for loan applicant | |
EP3859623A1 (en) | Risk vertex identification method and apparatus | |
CN111242656A (en) | User credit evaluation method and system based on telecommunication big data | |
CN111681090A (en) | Account grouping method and device of business system, terminal equipment and storage medium | |
CN112750030B (en) | Risk pattern recognition method, apparatus, device and computer readable storage medium | |
CN110046910B (en) | Method and equipment for judging validity of transaction performed by customer through electronic payment platform | |
WO2023087473A1 (en) | Service recovery priority evaluation method, device, storage medium, and product | |
CN113869781A (en) | Risk early warning method, device, equipment and readable storage medium | |
CN113095841A (en) | Transaction identification method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |