CN112396310A - Social credit risk assessment system based on machine learning - Google Patents
Social credit risk assessment system based on machine learning Download PDFInfo
- Publication number
- CN112396310A CN112396310A CN202011262949.0A CN202011262949A CN112396310A CN 112396310 A CN112396310 A CN 112396310A CN 202011262949 A CN202011262949 A CN 202011262949A CN 112396310 A CN112396310 A CN 112396310A
- Authority
- CN
- China
- Prior art keywords
- sample data
- particle
- risk assessment
- model
- module
- 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.)
- Granted
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 56
- 238000010801 machine learning Methods 0.000 title claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 48
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 238000013210 evaluation model Methods 0.000 claims abstract description 12
- 238000012360 testing method Methods 0.000 claims abstract description 12
- 239000002245 particle Substances 0.000 claims description 49
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 238000000034 method Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims description 2
- 230000006399 behavior Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Educational Administration (AREA)
Abstract
The invention provides a social credit risk assessment system based on machine learning, which comprises: the sample data module is used for acquiring personal social credit sample data, wherein the sample data comprises personal basic information and personal credit information; a model training module user inputs training sample data into the risk assessment model as a training set for model training to generate a trained risk assessment model; the input module is used for acquiring basic information of a target individual as target test data; the evaluation module is used for calling the trained risk evaluation model in the model training module, inputting the target test data into the trained risk evaluation model and obtaining the risk evaluation result output by the risk evaluation model. The risk assessment model with high accuracy can be used as the risk assessment of the target object based on the machine learning automatic training model, and a reference basis is provided for the personal social credit risk assessment of the target object.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to a social credit risk assessment system based on machine learning.
Background
Currently, for the evaluation of personal social credit, the credit rating of the target individual is usually evaluated in a subjective manner according to the specific credit keeping behavior record or credit losing behavior record of the target individual as a basis; however, for a target object without any credit-keeping behavior record or credit-losing behavior record, the basis of credit rating is lost, and the requirement of credit information inquiry or evaluation in the modern society cannot be met.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a social credit risk assessment system based on machine learning.
The purpose of the invention is realized by adopting the following technical scheme:
provided is a social credit risk assessment system based on machine learning, including:
the sample data module is used for acquiring personal social credit sample data, wherein the sample data comprises personal basic information and personal credit information;
the statistical module is used for acquiring the personal social credit sample data in the sample data module as training sample data when the number of the personal social credit sample data in the sample data module is greater than a set threshold value;
the model training module is used for inputting training sample data into the risk assessment model as a training set by a user for model training to generate a trained risk assessment model;
the input module is used for acquiring basic information of a target individual as target test data;
and the evaluation module is used for calling the trained risk evaluation model in the model training module, inputting the target test data into the trained risk evaluation model and acquiring the risk evaluation result output by the risk evaluation model.
The invention has the beneficial effects that: the risk assessment system manages the acquired personal social credit data to form a sample library, trains a risk assessment model according to the sample data, adopts the risk assessment model to assess the risk of the target object, can be used as the risk assessment of the target object based on the risk assessment model with high machine learning automatic training accuracy, and provides a reference basis for the personal social credit risk assessment of the target object.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
Fig. 1 is a frame structure diagram of the present invention.
Reference numerals:
sample data module 100, statistics module 200, model training module 300, input module 400, evaluation module 500
Detailed Description
The invention is further described in connection with the following application scenarios.
Referring to fig. 1, a machine learning based social credit risk assessment system is shown, comprising:
the sample data module 100 is configured to obtain sample data of personal social credit, where the sample data includes personal basic information and personal credit information;
a statistics module 200, configured to obtain personal social credit sample data in the data module as training sample data when the number of the personal social credit sample data in the sample data module 100 is greater than a set threshold;
the model training module 300 is used for inputting training sample data into the risk assessment model as a training set by a user for model training to generate a trained risk assessment model;
an input module 400 for acquiring basic information of a target individual as target test data;
the evaluation module 500 is configured to invoke the trained risk evaluation model in the model training module 300, input the target test data into the trained risk evaluation model, and obtain a risk evaluation result output by the risk evaluation model.
Wherein, the personal basic information comprises: age, marital status, native place, place of residence, work unit, historical credit-keeping events, historical loss-of-credit events, etc.; the personal credit information includes: credit rating, etc.
In the above embodiment, the sample data module 100 manages the acquired personal social credit data to form a sample library, the model training module 300 trains the risk assessment model according to the sample data, the assessment module 500 performs risk assessment on the target object by using the risk assessment model, and the risk assessment model with high accuracy can be automatically trained based on machine learning and used as risk assessment of the target object, so as to provide a reference basis for personal social credit risk assessment of the target object.
In one embodiment, the sample data module 100 further comprises:
the external unit is used for importing personal social credit sample data from a personal social credit inquiry platform database; and/or
And the recording unit is used for recording personal social credit sample data.
The personal social credit sample data can be imported into the risk assessment system through a database (or other personal social credit data open source databases and the like) of a personal social credit inquiry platform which is disclosed from the outside, and meanwhile, an internal database can be built in the risk assessment system, and the personal social credit sample data is input into the system through an input mode.
In one embodiment, the statistics module 200 further comprises:
and (3) performing data cleaning on the personal social credit sample data in the sample data module 100, eliminating invalid data in the personal social credit sample data, and converting the personal social credit sample data into a format conforming to training sample data.
For the human social credit sample data of the road in the starting database, the imported data volume may be huge, and error data or useless data easily exist, so the system of the invention is provided with the statistical module 200 and is also used for carrying out pretreatment such as data cleaning on the imported human social credit sample data, and the like, so that the human social credit sample data is converted into a uniform training sample data format, and the subsequent calling and management of the system are facilitated.
In the sample data, the personal basic information contained in the sample data can be in a data form of category attributes, such as whether the sample data is married, the place where the sample data is resident, the category of historical lost mail events and the like; or may be in the form of data with numerical attributes such as age, historical amount of time spent, etc. The data format can meet the requirement of risk assessment model training.
In one embodiment, the model training module 300 can train the risk assessment model using existing model training methods.
In addition, in order to improve the performance of the risk assessment model, the present invention further provides an improved model training solution, and in one embodiment, the model training module 300 includes:
determining a topological structure of a BP neural network model adopted in a risk assessment model, and taking training sample data acquired by a statistical module 200 as a training set;
carrying out initialization setting on the particle swarm, comprising the following steps: setting an initial iteration time T to be 0, setting a population size N, setting a search space dimension d, setting a training maximum iteration time T, setting upper and lower boundary thresholds of an inertia weight omega, and setting an initial position x of a particlei＝{xi1,xi2,…,xidAnd initial velocity vi＝{vi1,vi2,…,vidWhere I ═ 1,2, …, I denotes the total number of particles, xidAnd vidRepresenting the position and the speed of the particle i in the d-dimension, wherein the position of the particle corresponds to the weight and the threshold of a group of neural networks, the position thresholds x 'max and x' min of the particle are set, and the speed thresholds v 'max and v' min of the particle are set;
initializing the optimal historical location x for each particlei-bestCalculating a preferred value Q of each particleiInitializing a population optimal position p according to the preferred value of each particlebestAnd the position p of the opposite side of the populationworst；
Preferred value of Q of the particles thereiniIs calculated as
In the formula, QiThe preferred value of the current position of the ith particle is represented, R represents the number of training sample data in the sample set, J represents the total number of output nodes in the neural network, J represents the jth output node in the neural network, and gamma isrjRepresents the expected output value, y, of the jth output node in the neural networkrj(t) represents an actual output value of the jth output node;
wherein when t is 0, xi-best＝xi，pbest＝xaWherein
pworst＝xbWherein
And (3) an iterative process: updating the current iteration round number t to t + 1;
updating the position and velocity of each particle, wherein the update function used is:
vi(t)＝ωvi(t-1)+c1(xi-best(t-1)-xi(t-1))+c2(pbest(t-1)-xi(t-1))+c3(pworst(t-1)-xi(t-1))
xi(t)＝xi(t-1)+vi(t)
in the formula, vi(t) represents the velocity of the ith particle in the t iteration, vi(t-1) represents the velocity of the ith particle in the t-1 th iteration, xi(t) denotes the position of the ith particle in the t-th iteration, xi(t-1) denotes the position of the ith particle in the t-1 th iteration, and ω denotes the trend weight, where
T represents a set maximum number of iterations, where c1、c2、c3To control the factor, c1Is [0.3,0.7 ]]Random number in between, c2Is [0.2,0.5 ]]Random number in between, c1Is [0.1,0.9 ]]A random number in between;
respectively calculating the optimized value Q of each particle after the position updateiWhen the preferred value of the particle i in the current iteration round number is less than the optimal historical position x of the particlei-bestWhen the corresponding optimal value is reached, the historical optimal position x of the particle is updatedi-best＝xi(t); if the preferred value of the particle i in the current iteration round number is smaller than the optimal position p of the populationbestWhen the corresponding optimal value is obtained, the optimal position p of the population is updatedbest＝xi(t) if there is a preferred value of particle i in the current iteration round greater than the population negative position pworstWhen the corresponding optimal value is reached, the back side position p of the population is updatedworst＝xi(t)；
Judging whether the current iteration times reach the set maximum iteration times T, if not, repeating the iteration process to carry out a new iteration; if yes, ending the iteration process and enabling the current population to be at the optimal position pbestAnd mapping to the weight and the threshold of the neural network, and outputting the trained risk assessment model.
In the above embodiment, a technical scheme for training a risk assessment model is provided, in which, in a technical scheme for model training based on a BP neural network, an update rule of particles is particularly improved, and by adding a population back position as an influencing factor of the particles in each iteration process and providing an improved control factor setting method, the stimulation of the particles to break the constraint caused by a local optimal solution can be facilitated, and the performance of the model for finding the optimal solution in the training process is improved.
In one embodiment, the input module 400 includes:
and acquiring basic information corresponding to the target individual from an open source database according to the target individual information input by the user, and taking the acquired target individual basic information as target test data.
In one scenario, a user inputs the name or identity ID information of a target individual through the input module 400, and obtains basic information corresponding to the target individual from an internal database or a development database according to the name or ID information of the target individual, wherein the basic information includes age, marital status, native place, residence, work units, historical credit-keeping events, historical loss-of-credit events, and the like; the personal credit information includes: credit rating, etc.; and generating target test data according to the information, wherein the target test data conforms to the format of the input data of the risk assessment model, and each item of basic information is used as a characteristic parameter of the input data.
In one embodiment, the evaluation module 500 further comprises:
and displaying the risk assessment result. The assessment module 500 outputs a risk assessment result output by the risk assessment model, wherein the risk assessment result includes an assessed credit rating.
In the above embodiment, the risk assessment system of the present invention can adaptively perform the training of the risk assessment model according to the personal social credit sample data, and perform the credit rating assessment on the target object using the finally trained risk assessment model, and can effectively obtain the credit assessment result with strong objectivity according to the basic situation of the target object, provide a basis for the credit rating of the relevant department or user on the target object, and simultaneously meet various requirements based on the personal social credit risk assessment.
It should be noted that, functional units/modules in the embodiments of the present invention may be integrated into one processing unit/module, or each unit/module may exist alone physically, or two or more units/modules are integrated into one unit/module. The integrated units/modules may be implemented in the form of hardware, or may be implemented in the form of software functional units/modules.
From the above description of embodiments, it is clear for a person skilled in the art that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For a hardware implementation, a processor may be implemented in one or more of the following units: an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof. For a software implementation, some or all of the procedures of an embodiment may be performed by a computer program instructing associated hardware. In practice, the program may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. Computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be analyzed by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (6)
1. A machine learning based social credit risk assessment system, comprising:
the sample data module is used for acquiring personal social credit sample data, wherein the sample data comprises personal basic information and personal credit information;
the statistical module is used for acquiring the personal social credit sample data in the sample data module as training sample data when the number of the personal social credit sample data in the sample data module is greater than a set threshold value;
the model training module is used for inputting training sample data into the risk assessment model as a training set by a user for model training to generate a trained risk assessment model;
the input module is used for acquiring basic information of a target individual as target test data;
and the evaluation module is used for calling the trained risk evaluation model in the model training module, inputting the target test data into the trained risk evaluation model and acquiring the risk evaluation result output by the risk evaluation model.
2. The machine learning-based social credit risk assessment system according to claim 1, wherein said sample data module further comprises:
the external unit is used for importing personal social credit sample data from a personal social credit inquiry platform database; and/or
And the recording unit is used for recording the personal social credit sample data.
3. The machine learning-based social credit risk assessment system according to claim 1, wherein said statistics module further comprises:
and performing data cleaning on the personal social credit sample data in the sample data module, eliminating invalid data in the personal social credit sample data, and converting the personal social credit sample data into a format conforming to the training sample data.
4. The machine learning-based social credit risk assessment system according to claim 1, wherein said model training module comprises:
determining a topological structure of a BP neural network model adopted in a risk assessment model, and taking training sample data obtained by a statistical module as a training set;
carrying out initialization setting on the particle swarm, comprising the following steps: setting the initial iteration time T to be 0, setting the population size N, setting the search space dimension d, setting the training maximum iteration time T, and setting the upper and lower boundary thresholds of the inertia weight omegaValue, set initial position x of particlei＝{xi1，xi2，...，xidAnd initial velocity vi＝{vi1，vi2，...，vidWhere I ═ 1, 2.., I denotes the total number of particles, xidAnd vidRepresenting the position and the speed of the particle i in the d-dimension, wherein the position of the particle corresponds to the weight and the threshold of a group of neural networks, the position thresholds x 'max and x' min of the particle are set, and the speed thresholds v 'max and v' min of the particle are set;
initializing the optimal historical location x for each particlei-bestCalculating a preferred value Q of each particleiInitializing a population optimal position p according to the preferred value of each particlebestAnd the position p of the opposite side of the populationworst；
Preferred value of Q of the particles thereiniIs calculated as
In the formula, QiThe preferred value of the current position of the ith particle is represented, R represents the number of training sample data in the sample set, J represents the total number of output nodes in the neural network, J represents the jth output node in the neural network, and gamma isrjRepresents the expected output value, y, of the jth output node in the neural networkΥj(t) represents an actual output value of the jth output node;
wherein when t is 0, xi-best＝xi，pbest＝xaWherein
pworst＝xbWherein
And (3) an iterative process: updating the current iteration round number t to t + 1;
updating the position and velocity of each particle, wherein the update function used is:
vi(t)＝ωvi(t-1)+c1(xi-best(t-1)-xi(t-1))+c2(pbest(t-1)-xi(t-1))+c3(pworst(t-1)-xi(t-1))
xi(t)＝xi(t-1)+vi(t)
in the formula, vi(t) represents the velocity of the ith particle in the t iteration, vi(t-1) represents the velocity of the ith particle in the t-1 th iteration, xi(t) denotes the position of the ith particle in the t-th iteration, xi(t-1) denotes the position of the ith particle in the t-1 th iteration, and ω denotes the trend weight, where
T represents a set maximum number of iterations, where c1、c2、c3To control the factor, c1Is [0.3,0.7 ]]Random number in between, c2Is [0.2,0.5 ]]Random number in between, c1Is [0.1,0.9 ]]A random number in between;
respectively calculating the optimized value Q of each particle after the position updateiWhen the preferred value of the particle i in the current iteration round number is less than the optimal historical position x of the particlei-bestWhen the corresponding optimal value is reached, the historical optimal position x of the particle is updatedi-best＝xi(t); if the preferred value of the particle i in the current iteration round number is smaller than the optimal position p of the populationbestWhen the corresponding optimal value is obtained, the optimal position p of the population is updatedbest＝xi(t) if there is a preferred value of particle i in the current iteration round greater than the population negative position pworstWhen the corresponding optimal value is reached, the back side position p of the population is updatedworst＝xi(t)；
Judging whether the current iteration times reach the set maximum iteration times T, if not, repeating the iteration process to carry out a new iteration; if yes, ending the iteration process and enabling the current population to be at the optimal position pbestMapping to weight and threshold of neural network, and outputting trainingThe risk assessment model of (1).
5. The machine learning-based social credit risk assessment system according to claim 1, wherein said input module comprises:
and acquiring basic information corresponding to the target individual from an open source database according to the target individual information input by the user, and taking the acquired target individual basic information as the target test data.
6. The machine learning-based social credit risk assessment system according to claim 1, wherein said assessment module further comprises:
and displaying the risk assessment result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011262949.0A CN112396310B (en) | 2020-11-12 | 2020-11-12 | Social credit risk assessment system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011262949.0A CN112396310B (en) | 2020-11-12 | 2020-11-12 | Social credit risk assessment system based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112396310A true CN112396310A (en) | 2021-02-23 |
| CN112396310B CN112396310B (en) | 2024-05-28 |
Family
ID=74599901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011262949.0A Active CN112396310B (en) | 2020-11-12 | 2020-11-12 | Social credit risk assessment system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112396310B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702052A (en) * | 2023-08-02 | 2023-09-05 | 云南香农信息技术有限公司 | Community social credit system information processing system and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670940A (en) * | 2018-11-12 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Credit Risk Assessment Model generation method and relevant device based on machine learning |
| CN110610412A (en) * | 2019-09-02 | 2019-12-24 | 深圳中兴飞贷金融科技有限公司 | Credit risk assessment method and device, storage medium and electronic equipment |
| CN110992173A (en) * | 2020-03-04 | 2020-04-10 | 杭州信雅达数码科技有限公司 | Credit risk assessment model generation method based on multi-instance learning |
| CN111080397A (en) * | 2019-11-18 | 2020-04-28 | 支付宝(杭州)信息技术有限公司 | Credit evaluation method and device and electronic equipment |
-
2020
- 2020-11-12 CN CN202011262949.0A patent/CN112396310B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670940A (en) * | 2018-11-12 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Credit Risk Assessment Model generation method and relevant device based on machine learning |
| CN110610412A (en) * | 2019-09-02 | 2019-12-24 | 深圳中兴飞贷金融科技有限公司 | Credit risk assessment method and device, storage medium and electronic equipment |
| CN111080397A (en) * | 2019-11-18 | 2020-04-28 | 支付宝(杭州)信息技术有限公司 | Credit evaluation method and device and electronic equipment |
| CN110992173A (en) * | 2020-03-04 | 2020-04-10 | 杭州信雅达数码科技有限公司 | Credit risk assessment model generation method based on multi-instance learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702052A (en) * | 2023-08-02 | 2023-09-05 | 云南香农信息技术有限公司 | Community social credit system information processing system and method |
| CN116702052B (en) * | 2023-08-02 | 2023-10-27 | 云南香农信息技术有限公司 | Community social credit system information processing system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112396310B (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109636061B (en) | Training method, device and equipment for medical insurance fraud prediction network and storage medium | |
| CN108491928B (en) | Model parameter sending method, device, server and storage medium | |
| WO2023035564A1 (en) | Load interval prediction method and system based on quantile gradient boosting decision tree | |
| US20190057320A1 (en) | Data processing apparatus for accessing shared memory in processing structured data for modifying a parameter vector data structure | |
| CN109558951A (en) | A kind of fraud account detection method, device and its storage medium | |
| CN114048331A (en) | Knowledge graph recommendation method and system based on improved KGAT model | |
| WO2021089013A1 (en) | Spatial graph convolutional network training method, electronic device and storage medium | |
| CN109564641B (en) | Data filling method and device | |
| CN104965890A (en) | Advertisement recommendation method and apparatus | |
| CN110993118A (en) | Epidemic situation prediction method, device, equipment and medium based on ensemble learning model | |
| US10467221B2 (en) | Software function verification system and software function verification method | |
| US20210073628A1 (en) | Deep neural network training method and apparatus, and computer device | |
| JP6199461B1 (en) | Information processing apparatus, information processing method, and program | |
| CN108257670A (en) | The method for building up and device of medical explanation model | |
| CN112365007A (en) | Model parameter determination method, device, equipment and storage medium | |
| CN113379071A (en) | Noise label correction method based on federal learning | |
| CN109871866B (en) | Model training method, device, equipment and medium for hospital infection prediction | |
| CN112396310A (en) | Social credit risk assessment system based on machine learning | |
| CN108647714A (en) | Acquisition methods, terminal device and the medium of negative label weight | |
| CN113221681B (en) | Model training method, action gesture generating method, device, equipment and medium | |
| WO2020034593A1 (en) | Method and apparatus for processing missing feature in crowd performance feature prediction | |
| CN111275059B (en) | Image processing method and device and computer readable storage medium | |
| CN111950237B (en) | Sentence rewriting method, sentence rewriting device and electronic equipment | |
| CN116243680A (en) | Black box domain adaptive industrial equipment diagnosis method, system and storage medium | |
| CN116188174A (en) | Insurance fraud detection method and system based on modularity and mutual information |
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 |