CN113554507A - Personal credit evaluation method and system based on back propagation neural network - Google Patents
Personal credit evaluation method and system based on back propagation neural network Download PDFInfo
- Publication number
- CN113554507A CN113554507A CN202110833581.7A CN202110833581A CN113554507A CN 113554507 A CN113554507 A CN 113554507A CN 202110833581 A CN202110833581 A CN 202110833581A CN 113554507 A CN113554507 A CN 113554507A
- Authority
- CN
- China
- Prior art keywords
- neural network
- information
- back propagation
- data
- obtaining
- 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.)
- Pending
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 36
- 238000011156 evaluation Methods 0.000 title claims abstract description 32
- 238000003062 neural network model Methods 0.000 claims abstract description 80
- 238000007781 pre-processing Methods 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000012502 risk assessment Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 41
- 238000006243 chemical reaction Methods 0.000 claims description 19
- 238000004140 cleaning Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 12
- 230000002950 deficient Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 11
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000003925 brain function Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction 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
- 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
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a personal credit evaluation method and a personal credit evaluation system based on a back propagation neural network, which are used for obtaining first data information of a first user; preprocessing the first data information through the data preprocessing unit, and then obtaining the preprocessed first data information; constructing a back propagation neural network model; obtaining first sample information based on a database; training the back propagation neural network model by using the first sample information; inputting the preprocessed first data information into the trained back propagation neural network model through the model implementation unit, and obtaining a first output result of the back propagation neural network model, wherein the first output result is a credit evaluation score of the first user. The technical problems that in the prior art, the credit rating assessment of the client has deviation and the credit risk assessment of the client cannot be scientifically and accurately performed are solved.
Description
Technical Field
The invention relates to the field related to personal credit assessment, in particular to a personal credit assessment method and system based on a back propagation neural network.
Background
When each bank and financial institution evaluates the personal credit risk, the personal credit risk evaluation is usually carried out through various application data actively submitted by the client, the historical data of the client accumulated in the financial institution and the data of the central bank credit investigation system, the indexes have single latitude, are graduated in content and poor in flexibility, and the change range of the measurement indexes over the years is small, so that the personal credit risk evaluation is difficult to completely fit with the rapidly developing financial industry.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
the technical problems that the assessment of the credit rating of the client has deviation and the credit risk assessment of the client cannot be scientifically and accurately carried out exist in the prior art.
Disclosure of Invention
The embodiment of the application provides the personal credit assessment method and the personal credit assessment system based on the back propagation neural network, solves the technical problems that in the prior art, deviation exists in the assessment of the client credit rating, and the credit risk assessment cannot be scientifically and accurately performed on the client, and achieves the technical effects of scientifically and accurately assessing the client credit rating, reducing the credit risk and saving high-quality clients.
In view of the foregoing problems, embodiments of the present application provide a personal credit assessment method and system based on a back propagation neural network.
In a first aspect, the present invention provides a personal credit assessment method based on a back propagation neural network, the method is applied to a risk assessment system, and the system has a data preprocessing unit, a model building unit, and a model implementation unit, wherein the method includes: acquiring first data information of a first user, wherein the first data information is to-be-processed data information; preprocessing the first data information through the data preprocessing unit, and then obtaining the preprocessed first data information; constructing a back propagation neural network model, wherein the back propagation neural network model comprises an input layer, an output layer and a hidden layer; obtaining first sample information based on a database; training the back propagation neural network model by using the first sample information; inputting the preprocessed first data information into the trained back propagation neural network model through the model implementation unit, and obtaining a first output result of the back propagation neural network model, wherein the first output result is a credit evaluation score of the first user.
In another aspect, the present application further provides a personal credit evaluation system based on a back propagation neural network, the system including: the device comprises a first obtaining unit, a second obtaining unit and a processing unit, wherein the first obtaining unit is used for obtaining first data information of a first user, and the first data information is to-be-processed data information; a second obtaining unit, configured to obtain the first data information after preprocessing the first data information by the data preprocessing unit; a first construction unit for constructing a back propagation neural network model, wherein the back propagation neural network model comprises an input layer, an output layer and a hidden layer; a third obtaining unit configured to obtain first sample information based on a database; a first training unit, configured to train the back propagation neural network model using the first sample information; a fourth obtaining unit, configured to input, by the model implementing unit, the preprocessed first data information into the trained back propagation neural network model, and obtain a first output result of the back propagation neural network model, where the first output result is a credit evaluation score of the first user.
In a third aspect, the present invention provides a personal credit evaluation system based on a back propagation neural network, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
due to the fact that the back propagation neural network model is constructed by preprocessing the first data information of the first user, the back propagation neural network model is trained according to the first sample information, the preprocessed first data information is input into the back propagation neural network model, a first output result of the back propagation neural network model is obtained, the first output result comprises the credit evaluation score of the first user, and the technical effects that the credit evaluation score of the user is more accurate, the credit risk is reduced, and a high-quality client is saved are achieved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
FIG. 1 is a schematic flow chart of a personal credit evaluation method based on a back propagation neural network according to an embodiment of the present application;
FIG. 2 is a schematic structural diagram of a personal credit evaluation system based on a back propagation neural network according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a first constructing unit 13, a third obtaining unit 14, a first training unit 15, a fourth obtaining unit 16, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 306.
Detailed Description
The embodiment of the application provides the personal credit assessment method and the personal credit assessment system based on the back propagation neural network, solves the technical problems that in the prior art, deviation exists in the assessment of the client credit rating, and the credit risk assessment cannot be scientifically and accurately performed on the client, and achieves the technical effects of scientifically and accurately assessing the client credit rating, reducing the credit risk and saving high-quality clients. Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
When each bank and financial institution evaluates the personal credit risk, the personal credit risk evaluation is usually carried out through various application data actively submitted by the client, the historical data of the client accumulated in the financial institution and the data of the central bank credit investigation system, the indexes have single latitude, are graduated in content and poor in flexibility, and the change range of the measurement indexes over the years is small, so that the personal credit risk evaluation is difficult to completely fit with the rapidly developing financial industry. However, the technical problems that the credit rating assessment of the client has deviation and the credit risk assessment of the client cannot be scientifically and accurately performed exist in the prior art.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides a personal credit assessment method based on a back propagation neural network, which is applied to a risk assessment system, and the system is provided with a data preprocessing unit, a model construction unit and a model implementation unit, wherein the method comprises the following steps: acquiring first data information of a first user, wherein the first data information is to-be-processed data information; preprocessing the first data information through the data preprocessing unit, and then obtaining the preprocessed first data information; constructing a back propagation neural network model, wherein the back propagation neural network model comprises an input layer, an output layer and a hidden layer; obtaining first sample information based on a database; training the back propagation neural network model by using the first sample information; inputting the preprocessed first data information into the trained back propagation neural network model through the model implementation unit, and obtaining a first output result of the back propagation neural network model, wherein the first output result is a credit evaluation score of the first user.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, the embodiment of the present application provides a personal credit assessment method based on a back propagation neural network, which is applied to a risk assessment system, and the system has a data preprocessing unit, a model construction unit, and a model implementation unit, wherein the method includes:
step S100: acquiring first data information of a first user, wherein the first data information is to-be-processed data information;
specifically, the first user is a user to be credit risk evaluated by a bank or a financial institution, the first data information is related data information of the first user, and the data information is acquired by the first user.
Step S200: preprocessing the first data information through the data preprocessing unit, and then obtaining the preprocessed first data information;
specifically, the preprocessing unit is a unit that preprocesses the acquired first data of the first user, where the preprocessing includes data cleaning, data conversion, data normalization, and the like.
Step S300: constructing a back propagation neural network model, wherein the back propagation neural network model comprises an input layer, an output layer and a hidden layer;
in particular, Neural Networks (NN) are complex neural network systems formed by a large number of simple processing units (called neurons) widely connected to each other, reflect many basic features of human brain functions, and are highly complex nonlinear dynamical learning systems. Neural network models are described based on mathematical models of neurons. Artificial neural networks (artifical neural networks) are a description of the first-order properties of the human brain system. Briefly, it is a mathematical model.
Further, in the building of the back propagation neural network model, step S300 in the embodiment of the present application further includes:
step S310: obtaining a first input node number of the input layer in the back propagation neural network model by adopting a frog leap algorithm;
step S320: obtaining a first output node number of the output layer in the back propagation neural network model by adopting the leapfrog algorithm;
step S330: obtaining a first hidden node number of the hidden layer in the back propagation neural network model;
step S340: and constructing the back propagation neural network model according to the first input node number, the first output node number and the first hidden node number.
Specifically, the back propagation neural network model is trained by using a 3-layer back propagation neural network, because the training effect is easier to achieve by increasing the number of nodes of the hidden layer to obtain a lower error than by increasing the number of hidden layers of the model. Confirming the number of the first input nodes, namely selecting the number of indexes: and selecting attributes such as age, gender, marital condition, cultural degree, housing property, occupation, service life, job title, annual income, relation with the bank, credit card holding condition and the like as nodes for training by combining credit evaluation indexes popular in the industry. In the embodiment of the present application, five risk levels are adopted to determine the first output node number of the model, so that the node number of the selected output layer is 5. And introducing a leapfrog algorithm, wherein the BP algorithm neural network is easily trapped into a local minimum value due to the constraint of an initial weight and a threshold value, the leapfrog algorithm is used for leapfrog out of the limit, a global extreme value is finally found, and the back propagation neural network model is finally constructed according to the first input node number, the first output node number and the first hidden node number.
Step S400: obtaining first sample information based on a database;
specifically, the database is obtained by combining data of a bank system, and based on the database, suitable sample information is searched, wherein the sample information is sample information with reference value formed on the basis of the personal information, behavior habits, customer historical data accumulated inside a financial institution, a plurality of influence factors and personal credit risk assessment results.
Step S500: training the back propagation neural network model by using the first sample information;
step S600: inputting the preprocessed first data information into the trained back propagation neural network model through the model implementation unit, and obtaining a first output result of the back propagation neural network model, wherein the first output result is a credit evaluation score of the first user.
Specifically, the back propagation neural network model is trained according to the first sample information, the back propagation neural network model is continuously self-corrected and adjusted according to the training result, so as to obtain more accurate experience processing input data, the simulation implementation unit inputs the first data information into the trained back propagation neural network model, so as to obtain a first output result of the back propagation neural network model, and the first output result includes a credit evaluation score of the first user. By training the back propagation neural network model and inputting the first data information into the trained back propagation neural network model, a first output result of the back propagation neural network model is obtained, wherein the first output result comprises a credit evaluation score of the first user, so that the technical effects of more accurately evaluating the credit evaluation score of the user, reducing credit risk and saving high-quality clients are achieved.
Further, in the step S200 in this embodiment of the present application, after the preprocessing the first data information by the data preprocessing unit, the first data information after being preprocessed is obtained, the method further includes:
step S210: obtaining a first data cleaning instruction;
step S220: judging whether invalid data and/or defective data exist in the first data information according to the first data cleaning instruction;
step S230: and if so, deleting the invalid data and/or the defective data.
Specifically, the obtaining of the first data cleaning instruction is to determine the first data information, actually, in the acquired data, to determine integrity and validity of the data, and when there is incomplete data, that is, defective data, in the acquired data, delete the defective data, and if invalid data is detected, delete the invalid data according to the first data cleaning instruction. The data cleaning is carried out on the first data, so that the technical effect of guaranteeing the integrity and reliability of the data is achieved, and a foundation is laid for obtaining accurate credit assessment scores of the user subsequently.
Further, after deleting the invalid data and/or the defective data if the invalid data exists, step S230 in this embodiment of the present application further includes:
step S231: judging whether first type index information exists in the first data information after cleaning, wherein the first type index information is non-numerical value type information;
step S232: if so, obtaining a first translation instruction;
step S233: and converting the first type index information according to the first conversion instruction to obtain second type index information, wherein the second type index information is numerical value type information.
Further, the step S233 in this embodiment of the present application further includes, according to the first conversion instruction, converting the first type index information in the first data information after the cleaning to obtain a second type index information:
step S2331: obtaining preset conversion value list information;
step S2332: acquiring first numerical value information of the first type index information according to the preset conversion numerical value list information;
step S2333: and obtaining second type index information according to the first numerical value information.
Specifically, the first type index information specifically refers to non-numerical information, and when the non-numerical information exists in the first data information, the non-numerical information is converted into numerical information according to the first conversion instruction, where a specific conversion manner is as follows: first, obtaining preset conversion value list information, wherein the preset conversion value list information is different value information corresponding to different preset classification index information, namely, list information obtained according to the classification of the first data or the required data classification, and a value appearing at a corresponding position represents information of the position. For example, converting a non-numeric value to a numeric value, such as a scholarly conversion, is, master: 10, this family: 7, major: 5, high school and the following: 2; stability of the work unit, national organs/institutions: 10, enterprises of three enterprises: 7, civil camp: 5, private: and 4, converting the corresponding information in the first data into corresponding numerical information for substitution, and laying a foundation for subsequent convenience in calculation of the first data.
Further, the embodiment of the present application further includes:
step S240: judging whether third type index information exists in the first data information after cleaning, wherein the third type index information comprises index information of multiple dimensions;
step S250: if so, obtaining a first normalization instruction;
step S260: according to the first normalization instruction, normalization processing is carried out on the index information of the multiple dimensions in the third type of index information so as to balance differences among the index information of the multiple dimensions.
Specifically, the index information of the multiple dimensions, namely age, loan amount, credit card amount, internet authentication recording times, online annual expenditure total amount and the like exist at the same time, and the real values of the index information are substituted into calculation, namely normalization processing is carried out, so that the technical effect of balancing the difference between indexes of different dimensions is achieved.
Further, in the step S330 of obtaining the first hidden node number of the hidden layer in the back propagation neural network model, the method further includes:
step S331: obtaining a first initial node number;
step S332: obtaining a first adjusting instruction;
step S333: adjusting the first initial node number according to the first adjusting instruction and a first calculation formula to obtain the first hidden node number, wherein the first calculation formula comprises: l<n-1、
And l is the number of the first hidden nodes, n is the number of the first input nodes, k is the number of the first output nodes, and the value range of i is any number between 0 and 9.
Specifically, the determination of the number of hidden nodes is set according to experience or a trial and error method, that is, according to the first adjustment instruction and the first calculation formula, the number of initial nodes of the hidden layer is obtained through calculation, and the number of initial nodes of the hidden layer is continuously adjusted through the trial and error method. And then, introducing a leapfrog algorithm, wherein the BP algorithm neural network is easily trapped into a local minimum value due to the constraint of an initial weight and a threshold value, jumping out of the limit by using the leapfrog algorithm, finally finding a global extreme value, training the model through sample data, inputting the first data information into the trained back propagation neural network model, and obtaining a first output result of the back propagation neural network model, wherein the first output result comprises a credit evaluation score of the first user, so that the credit evaluation score of the user is more accurate, the credit risk is reduced, and the technical effect of high-quality customers is saved.
In summary, the personal credit assessment method and system based on the back propagation neural network provided by the embodiment of the present application have the following technical effects:
1. due to the fact that the back propagation neural network model is constructed by preprocessing the first data information of the first user, the back propagation neural network model is trained according to the first sample information, the preprocessed first data information is input into the back propagation neural network model, a first output result of the back propagation neural network model is obtained, the first output result comprises the credit evaluation score of the first user, and the technical effects that the credit evaluation score of the user is more accurate, the credit risk is reduced, and a high-quality client is saved are achieved.
2. Due to the adoption of the mode of cleaning the first data, the technical effect of ensuring the integrity and the reliability of the data is achieved, and a foundation is laid for obtaining accurate credit assessment scores of the user subsequently.
3. Due to the adoption of the mode of normalization processing, the technical effect of balancing the difference between different dimensional indexes is achieved.
Example two
Based on the same inventive concept as the personal credit assessment method based on the back propagation neural network in the foregoing embodiment, the present invention further provides a personal credit assessment system based on the back propagation neural network, as shown in fig. 2, the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain first data information of a first user, where the first data information is to-be-processed data information;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain the first data information after preprocessing the first data information by a data preprocessing unit;
a first constructing unit 13, where the first constructing unit 13 is configured to construct a back propagation neural network model, where the back propagation neural network model includes an input layer, an output layer, and a hidden layer;
a third obtaining unit 14, wherein the third obtaining unit 14 is configured to obtain the first sample information based on the database;
a first training unit 15, where the first training unit 15 is configured to train the back propagation neural network model by using the first sample information;
a fourth obtaining unit 16, where the fourth obtaining unit 16 is configured to input, through a model implementing unit, the preprocessed first data information into the trained back propagation neural network model, and obtain a first output result of the back propagation neural network model, where the first output result is a credit evaluation score of the first user.
Further, the system further comprises:
a fifth obtaining unit for obtaining a first data cleansing instruction;
the first judging unit is used for judging whether invalid data and/or defective data exist in the first data information according to the first data cleaning instruction;
a first deleting unit, configured to delete the invalid data and/or the defective data if the invalid data and/or the defective data exist.
Further, the system further comprises:
a second determining unit, configured to determine whether first type index information exists in the first data information after the cleaning, where the first type index information is non-numerical information;
a sixth obtaining unit to obtain the first conversion instruction, if any;
a first conversion unit, configured to convert the first type index information according to the first conversion instruction, and obtain second type index information, where the second type index information is numerical type information.
Further, the system further comprises:
a seventh obtaining unit configured to obtain preset conversion value list information;
an eighth obtaining unit, configured to obtain first numerical value information of the first type index information according to the preset conversion numerical value list information;
a ninth obtaining unit, configured to obtain second type index information according to the first numerical information.
Further, the system further comprises:
a third determining unit, configured to determine whether third type index information exists in the first data information after the cleaning, where the third type index information includes index information of multiple dimensions;
a tenth obtaining unit, configured to obtain, if present, a first normalization instruction;
a first processing unit, configured to perform normalization processing on the index information of the multiple dimensions in the third type of index information according to the first normalization instruction, so as to balance differences between the index information of the multiple dimensions.
Further, the system further comprises:
an eleventh obtaining unit, configured to obtain a first input node number of the input layer in the back propagation neural network model by using a frog-leap algorithm;
a twelfth obtaining unit, configured to obtain, by using the leapfrog algorithm, a first output node number of the output layer in the back propagation neural network model;
a thirteenth obtaining unit, configured to obtain a first hidden node number of the hidden layer in the back propagation neural network model;
and the second construction unit is used for constructing the back propagation neural network model according to the first input node number, the first output node number and the first hidden node number.
Further, the system further comprises:
a fourteenth obtaining unit, configured to obtain a first initial node number;
a fifteenth obtaining unit configured to obtain a first adjustment instruction;
a first adjusting unit, configured to adjust the first initial node number according to a first calculation formula according to the first adjustment instruction, to obtain the first hidden node number, where the first calculation formula includes: l<n-1、
And l is the number of the first hidden nodes, n is the number of the first input nodes, k is the number of the first output nodes, and the value range of i is any number between 0 and 9.
Various variations and specific examples of the personal credit assessment method based on the back propagation neural network in the first embodiment of fig. 1 are also applicable to the personal credit assessment system based on the back propagation neural network in the present embodiment, and through the foregoing detailed description of the personal credit assessment method based on the back propagation neural network, those skilled in the art can clearly understand the implementation method of the personal credit assessment system based on the back propagation neural network in the present embodiment, so for the brevity of the description, detailed description is not repeated here.
Exemplary electronic device
The electronic device of the embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of a personal credit assessment method based on a back propagation neural network as in the previous embodiments, the present invention further provides a personal credit assessment system based on a back propagation neural network, on which a computer program is stored, which when executed by a processor implements the steps of any one of the above-described personal credit assessment methods based on a back propagation neural network.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The embodiment of the invention provides a personal credit assessment method based on a back propagation neural network, which is applied to a risk assessment system, wherein the system is provided with a data preprocessing unit, a model construction unit and a model implementation unit, and the method comprises the following steps: acquiring first data information of a first user, wherein the first data information is to-be-processed data information; preprocessing the first data information through the data preprocessing unit, and then obtaining the preprocessed first data information; constructing a back propagation neural network model, wherein the back propagation neural network model comprises an input layer, an output layer and a hidden layer; obtaining first sample information based on a database; training the back propagation neural network model by using the first sample information; inputting the preprocessed first data information into the trained back propagation neural network model through the model implementation unit, and obtaining a first output result of the back propagation neural network model, wherein the first output result is a credit evaluation score of the first user. The technical problems that in the prior art, the assessment of the credit rating of the client has deviation and the credit risk assessment of the client cannot be scientifically and accurately performed are solved, and the technical effects of scientifically and accurately assessing the credit rating of the client, reducing the credit risk and saving the high-quality client are achieved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A personal credit assessment method based on a back propagation neural network is applied to a risk assessment system, and the system is provided with a data preprocessing unit, a model building unit and a model implementation unit, wherein the method comprises the following steps:
acquiring first data information of a first user, wherein the first data information is to-be-processed data information;
preprocessing the first data information through the data preprocessing unit, and then obtaining the preprocessed first data information;
constructing a back propagation neural network model, wherein the back propagation neural network model comprises an input layer, an output layer and a hidden layer;
obtaining first sample information based on a database;
training the back propagation neural network model by using the first sample information;
inputting the preprocessed first data information into the trained back propagation neural network model through the model implementation unit, and obtaining a first output result of the back propagation neural network model, wherein the first output result is a credit evaluation score of the first user.
2. The method of claim 1, wherein the obtaining the first data information after preprocessing the first data information by the data preprocessing unit comprises:
obtaining a first data cleaning instruction;
judging whether invalid data and/or defective data exist in the first data information according to the first data cleaning instruction;
and if so, deleting the invalid data and/or the defective data.
3. The method of claim 2, wherein after deleting the invalid data, and/or defective data, if any, the method further comprises:
judging whether first type index information exists in the first data information after cleaning, wherein the first type index information is non-numerical value type information;
if so, obtaining a first translation instruction;
and converting the first type index information according to the first conversion instruction to obtain second type index information, wherein the second type index information is numerical value type information.
4. The method of claim 3, wherein the converting, according to the first conversion instruction, the first type index information in the first data information after the cleaning to obtain second type index information, further comprises:
obtaining preset conversion value list information;
acquiring first numerical value information of the first type index information according to the preset conversion numerical value list information;
and obtaining second type index information according to the first numerical value information.
5. The method of claim 2, wherein the method further comprises:
judging whether third type index information exists in the first data information after cleaning, wherein the third type index information comprises index information of multiple dimensions;
if so, obtaining a first normalization instruction;
according to the first normalization instruction, normalization processing is carried out on the index information of the multiple dimensions in the third type of index information so as to balance differences among the index information of the multiple dimensions.
6. The method of claim 1, wherein the constructing a back propagation neural network model, the method further comprises:
obtaining a first input node number of the input layer in the back propagation neural network model by adopting a frog leap algorithm;
obtaining a first output node number of the output layer in the back propagation neural network model by adopting the leapfrog algorithm;
obtaining a first hidden node number of the hidden layer in the back propagation neural network model;
and constructing the back propagation neural network model according to the first input node number, the first output node number and the first hidden node number.
7. The method of claim 6, wherein the obtaining a first number of hidden nodes of a hidden layer in the back propagation neural network model comprises:
obtaining a first initial node number;
obtaining a first adjusting instruction;
adjusting the number of the first initial nodes according to the first adjusting instruction and a first calculation formula to obtain the first initial nodesA first number of hidden nodes, wherein the first calculation formula comprises: l<n-1、
And l is the number of the first hidden nodes, n is the number of the first input nodes, k is the number of the first output nodes, and the value range of i is any number between 0 and 9.
8. A personal credit evaluation system based on a back propagation neural network, wherein the system comprises:
the device comprises a first obtaining unit, a second obtaining unit and a processing unit, wherein the first obtaining unit is used for obtaining first data information of a first user, and the first data information is to-be-processed data information;
a second obtaining unit, configured to obtain the first data information after preprocessing, after preprocessing the first data information by a data preprocessing unit;
a first construction unit for constructing a back propagation neural network model, wherein the back propagation neural network model comprises an input layer, an output layer and a hidden layer;
a third obtaining unit configured to obtain first sample information based on a database;
a first training unit, configured to train the back propagation neural network model using the first sample information;
a fourth obtaining unit, configured to input, by a model implementing unit, the preprocessed first data information into the trained back propagation neural network model, and obtain a first output result of the back propagation neural network model, where the first output result is a credit evaluation score of the first user.
9. A personal credit assessment system based on a back propagation neural network comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110833581.7A CN113554507A (en) | 2021-07-23 | 2021-07-23 | Personal credit evaluation method and system based on back propagation neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110833581.7A CN113554507A (en) | 2021-07-23 | 2021-07-23 | Personal credit evaluation method and system based on back propagation neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113554507A true CN113554507A (en) | 2021-10-26 |
Family
ID=78132555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110833581.7A Pending CN113554507A (en) | 2021-07-23 | 2021-07-23 | Personal credit evaluation method and system based on back propagation neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113554507A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652701A (en) * | 2020-05-29 | 2020-09-11 | 蚌埠学院 | Personal credit evaluation method and system based on fusion neural network |
| CN112037012A (en) * | 2020-08-14 | 2020-12-04 | 百维金科(上海)信息科技有限公司 | Internet financial credit evaluation method based on PSO-BP neural network |
| CN112037011A (en) * | 2020-08-14 | 2020-12-04 | 百维金科(上海)信息科技有限公司 | Credit scoring method based on FOA-RBF neural network |
-
2021
- 2021-07-23 CN CN202110833581.7A patent/CN113554507A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652701A (en) * | 2020-05-29 | 2020-09-11 | 蚌埠学院 | Personal credit evaluation method and system based on fusion neural network |
| CN112037012A (en) * | 2020-08-14 | 2020-12-04 | 百维金科(上海)信息科技有限公司 | Internet financial credit evaluation method based on PSO-BP neural network |
| CN112037011A (en) * | 2020-08-14 | 2020-12-04 | 百维金科(上海)信息科技有限公司 | Credit scoring method based on FOA-RBF neural network |
Non-Patent Citations (3)
| Title |
|---|
| 冯婧: "基于BP神经网络的个人信用风险评估模型的研究", 中国优秀硕士学位论文全文数据库 信息科技辑, no. 01, 15 January 2018 (2018-01-15), pages 39 - 46 * |
| 张冠珠;刘朝东;: "改进BP神经网络在个人信用评估系统的应用", 齐齐哈尔大学学报, no. 05, 15 September 2008 (2008-09-15), pages 15 - 17 * |
| 黄文玲;方永美;邓成剑;: "基于BP神经网络的个人信用评价研究", 惠州学院学报, no. 03, 30 June 2006 (2006-06-30), pages 69 - 73 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sohaib et al. | A PLS-SEM neural network approach for understanding cryptocurrency adoption | |
| Wirawan et al. | Short term prediction on bitcoin price using ARIMA method | |
| US20140081832A1 (en) | System and method for building and validating a credit scoring function | |
| CN111967971B (en) | Bank customer data processing method and device | |
| US20230342846A1 (en) | Micro-loan system | |
| Kohli et al. | Construction and analysis of a global GDP growth model for 185 countries through 2050 | |
| Liang et al. | Best-worst tradeoff method | |
| CN112668822A (en) | Scientific and technological achievement transformation platform sharing system, method, storage medium and mobile phone APP | |
| Eddy et al. | Credit scoring models: Techniques and issues | |
| Murray et al. | Deep hedging: Continuous reinforcement learning for hedging of general portfolios across multiple risk aversions | |
| CN115511606A (en) | Object identification method, device, equipment and storage medium | |
| Yuan et al. | Credit risk assessment of peer-to-peer lending borrower utilizing BP neural network | |
| CN117575773A (en) | Method, device, computer equipment and storage medium for determining service data | |
| KR102519878B1 (en) | Apparatus, method and recording medium storing commands for providing artificial-intelligence-based risk management solution in credit exposure business of financial institution | |
| CN113554507A (en) | Personal credit evaluation method and system based on back propagation neural network | |
| CN109711848A (en) | A kind of matching system and its construction method, matching process of financial transaction | |
| US20220058658A1 (en) | Method of scoring and valuing data for exchange | |
| CN113706258A (en) | Product recommendation method, device, equipment and storage medium based on combined model | |
| Assa et al. | Assessing reinforcement delta hedging | |
| d’Andria | Tax policy and entrepreneurial entry with information asymmetry and learning | |
| CN115860889A (en) | Financial loan big data management method and system based on artificial intelligence | |
| CN113177733A (en) | Medium and small micro-enterprise data modeling method and system based on convolutional neural network | |
| US20200250474A1 (en) | System for estimating value of company using financial technology | |
| CN112862602B (en) | User request determining method, storage medium and electronic device | |
| CN113657915B (en) | Potential user recommendation method and device, electronic equipment and readable 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 |