CN113744045A - Client risk rating method and device, electronic equipment and computer storage medium - Google Patents
Client risk rating method and device, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN113744045A CN113744045A CN202111037989.XA CN202111037989A CN113744045A CN 113744045 A CN113744045 A CN 113744045A CN 202111037989 A CN202111037989 A CN 202111037989A CN 113744045 A CN113744045 A CN 113744045A
- Authority
- CN
- China
- Prior art keywords
- client
- customer
- risk
- data
- historical
- 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
- 238000000034 method Methods 0.000 title claims abstract description 76
- 239000011159 matrix material Substances 0.000 claims abstract description 80
- 238000013145 classification model Methods 0.000 claims abstract description 67
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000013598 vector Substances 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
- 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
- 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
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Technology Law (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and a device for rating a risk of a customer, electronic equipment and a computer storage medium, wherein the method comprises the steps of obtaining customer data; performing dimension reduction processing on the client data to determine a client characteristic value matrix; and taking the client characteristic value matrix as the input of a pre-constructed client grade classification model, and processing the client characteristic value matrix based on the pre-constructed client grade classification model to obtain the client risk grade, wherein the pre-constructed client grade classification model is obtained by training by using historical data. And outputting risk prompt information when the risk level of the client is determined to have risk. In the scheme, firstly, the customer data is subjected to dimensionality reduction to determine a customer characteristic value matrix; and then, processing the client characteristic value matrix by utilizing a client grade classification model which is constructed in advance to predict the risk grade of the client so as to classify the risk grade of the client. By the method, the classification accuracy and the classification speed of the risk level of the client can be improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for rating a risk of a customer, electronic equipment and a computer storage medium.
Background
With the increasing development of the internet industry, various financial activities which people can participate in directly or indirectly are increasing, and the financial behaviors are becoming more abundant. In order to maintain normal economic order and social stability, various regulatory agencies require that commercial banks judge the level of risk of customers.
At present, the risk level is often divided in a customer unit by a manual mode when the customer carries out transaction. The judgment speed is low through the mode, and errors are easy to occur in the manual dividing process, so that the processing efficiency is low and the condition is inaccurate.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for rating a risk of a customer, an electronic device, and a computer storage medium, so as to solve the problems of low processing efficiency and inaccuracy in the prior art.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
a first aspect of the present invention is directed to a method for rating a risk of a customer, the method comprising:
acquiring customer data, wherein the customer data at least comprises a transaction occurrence place, a transaction amount, a transaction date and a transaction affiliated line;
performing dimension reduction processing on the client data to determine a client characteristic value matrix;
the client characteristic value matrix is used as the input of a pre-constructed client grade classification model, and the client characteristic value matrix is processed based on the pre-constructed client grade classification model to obtain a client risk grade, wherein the pre-constructed client grade classification model is obtained by training through historical data;
and outputting risk prompt information when the risk level of the client is determined to have risk.
Optionally, the process of obtaining the data prediction model by training using the historical data includes:
acquiring historical data, wherein the historical data comprises historical transaction data of customers and historical customer rating results;
performing dimensionality reduction on the preprocessed historical data to determine a historical customer eigenvalue matrix;
and training a universal neural network model based on the historical customer characteristic value matrix and the historical customer rating result to obtain a customer grade classification model.
Optionally, the method further includes:
and after the client risk level is obtained, optimizing the client level classification model based on the client risk level.
Optionally, the performing the dimension reduction processing on the customer data to determine a customer eigenvalue matrix includes:
according to a preset index rule, the quantized value of the index in the client data is obtained;
and taking the quantized values of the indexes as client characteristic values, and combining the client characteristic values into a client characteristic value matrix.
A second aspect of an embodiment of the present invention shows a client risk rating apparatus, including:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring customer data, and the customer data at least comprises a transaction occurrence place, a transaction amount, a transaction date and a transaction affiliated line;
the processing unit is used for performing dimensionality reduction processing on the client data and determining a client characteristic value matrix;
the client grade classification model is used for taking the client characteristic value matrix as the input of a pre-constructed client grade classification model, processing the client characteristic value matrix based on the pre-constructed client grade classification model and obtaining a client risk grade, wherein the pre-constructed client grade classification model is constructed by utilizing a construction unit;
and the prompting unit is used for outputting risk prompting information when the risk level of the client is determined to have risk.
Optionally, the building unit includes:
the acquisition module is used for acquiring historical data, wherein the historical data comprises historical transaction data of a customer and a historical customer rating result;
the processing module is used for performing dimensionality reduction processing on the preprocessed historical data and determining a historical customer eigenvalue matrix;
and the training unit is used for training a universal neural network model based on the historical client characteristic value matrix and the historical client rating result to obtain a client grade classification model.
Optionally, the method further includes:
and the optimizing unit is used for optimizing the customer level classification model based on the customer risk level after obtaining the customer risk level.
Optionally, the processing unit is specifically configured to: according to a preset index rule, the quantized value of the index in the client data is obtained; and taking the quantized values of the indexes as client characteristic values, and combining the client characteristic values into a client characteristic value matrix.
A third aspect of the embodiments of the present invention shows an electronic device, where the electronic device is configured to run a program, where the program executes the method for rating a risk of a customer as shown in the first aspect of the embodiments of the present invention.
A fourth aspect of the embodiments of the present invention shows a computer storage medium, where the storage medium includes a storage program, where the storage medium is controlled, when the program runs, by a device in which the storage medium is located, to execute the client risk rating method shown in the first aspect of the embodiments of the present invention.
Based on the method, the device, the electronic equipment and the computer storage medium for rating the risk of the customer, provided by the embodiment of the invention, the method comprises the steps of obtaining customer data, wherein the customer data at least comprises a transaction occurrence place, a transaction amount, a transaction date and a transaction affiliated line; performing dimension reduction processing on the client data to determine a client characteristic value matrix; and taking the customer characteristic value matrix as the input of a pre-constructed customer grade classification model, and processing the customer characteristic value matrix based on the pre-constructed customer grade classification model to obtain a customer risk grade, wherein the pre-constructed customer grade classification model is obtained by training through historical data. And outputting risk prompt information when the risk level of the client is determined to have risk. In the embodiment of the invention, the customer data is subjected to dimensionality reduction to determine a customer characteristic value matrix; and then, processing the client characteristic value matrix by utilizing a client grade classification model which is constructed in advance to predict the risk grade of the client so as to classify the risk grade of the client. By the method, the classification accuracy and the classification speed of the risk level of the client can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart illustrating a method for rating a risk of a customer according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating the construction of a customer risk rating model according to an embodiment of the present invention;
FIG. 3 is a block diagram illustrating an architecture for training and using a customer-level classification model according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram illustrating a client risk rating apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of another client risk rating device according to an embodiment of the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In the embodiment of the invention, the customer data is subjected to dimensionality reduction to determine a customer characteristic value matrix; and then, processing the client characteristic value matrix by utilizing a client grade classification model which is constructed in advance to predict the risk grade of the client so as to classify the risk grade of the client. By the method, the classification accuracy and the classification speed of the risk level of the client can be improved.
Referring to fig. 1, a flow chart of a method for rating a risk of a customer according to an embodiment of the present invention is shown, the method including:
s101: customer data is acquired.
In step S101, the customer data includes at least a transaction venue, a transaction amount, a transaction date, and a transaction affiliated line.
In the process of implementing step S101, the data of the transaction place, the transaction amount, the transaction date, the transaction affiliated bank, and the like are obtained according to the customer data corresponding to the customer to be transacted.
S102: and performing dimension reduction processing on the client data to determine a client characteristic value matrix.
In the specific implementation process of step S102, the multi-source transaction data of the customer is reduced in dimension according to the index extraction rule to be converted into a customer transaction eigenvalue matrix.
It should be noted that the index extraction rule may be index 1, which takes the transaction amount of the client within 30 days, and in a specific implementation, the index right-lifting rule may have expansion, that is, the expansion index 1-1 of index 1 is the index of the transaction amount of the client in approximately 60 days, the expansion index 1-2 of index 1 is the transaction amount of the client in approximately 90 days, and the index 1-3 is the transaction amount of the client in approximately 180 days.
Dimension reduction is an operation performed on a single image converted into a data set in a high-dimensional space through high-dimensional transformation of single image data.
S103: and taking the customer characteristic value matrix as the input of a pre-constructed customer grade classification model, and processing the customer characteristic value matrix based on the pre-constructed customer grade classification model to obtain the risk grade of the customer.
In step S103, the pre-constructed customer level classification model is obtained by training using historical data.
It should be noted that, the pre-construction process of training to obtain the customer-level classification model by using historical data, as shown in fig. 2, includes the following steps:
correspondingly, the embodiment of the application also discloses an architecture diagram for training and using the customer grade classification model, as shown in fig. 3.
S201: historical data is acquired.
In step S201, the historical data includes historical transaction data of the customer and historical customer rating results.
In the process of implementing step S201 specifically, various information in the historical transaction data is collected and marked, and a marked sample set is constructed, that is, the data in the sample set is marked as a customer rating result, and various information affecting the rating result, such as a customer rating result, a transaction place, a transaction amount, a transaction date, a transaction affiliated row, and the like.
S202: and performing dimensionality reduction on the preprocessed historical data to determine a historical customer eigenvalue matrix.
In the process of implementing step S202, the historical data is preprocessed first; and then, reducing the dimension of the multi-source transaction data of the client according to an index extraction rule so as to convert the multi-source transaction data into a historical client transaction characteristic value matrix.
In the embodiment of the invention, the specific implementation process of reducing the dimension of the multi-source transaction data of the client according to the index extraction rule to convert the multi-source transaction data into the historical client transaction characteristic value matrix comprises the steps of quantifying the index in the client data according to a preset index rule, taking the quantified value of the index as the client characteristic value, and combining the client characteristic value into the client characteristic value matrix.
It should be noted that the specific implementation process of step S202 is the same as the specific implementation process of step S102 shown above, and reference may be made to each other.
S203: and training a universal neural network model based on the historical customer characteristic value matrix and the historical customer rating result to obtain a customer grade classification model.
In the process of implementing step S203 specifically, the historical client rating results corresponding to the historical client eigenvalue matrix and the historical client eigenvalue matrix are divided into K groups, each group of the historical client eigenvalue matrix and the historical client rating results corresponding to the historical client eigenvalue matrix are made into a primary verification set, and the historical client eigenvalue matrix and the historical client rating results of the remaining K-1 groups are used as a training set. Based on the neural network model determination, corresponding initial network parameters are configured. And training initial network parameters by using the first group of training sets, and verifying the client grade classification model constructed based on the initial network parameters by using a verification set. And the like until the cross validation is repeated k times.
When each training set is used for verifying the customer grade classification model constructed based on the initial network parameters, corresponding verification results need to be obtained, the average value of k verification results is taken to optimize the network parameters, the generalization errors can be reduced, and the customer grade classification model is constructed based on the optimized network parameters.
It should be noted that the historical customer feature value matrix and the historical customer rating result of the same customer are in the same data set, such as: the historical customer eigenvalue matrix and the historical customer rating result of the customer A are in a training set.
In the process of implementing step S103 specifically, the customer eigenvalue matrix is input into the framework of the customer class classification model trained in fig. 3, so that the customer class classification model processes the customer eigenvalue matrix to obtain a customer risk class, and classifies the customer risk class.
It should be noted that the types of the risk level of the client include low, medium and high types.
S104: and judging whether the risk level of the client has a risk, if so, executing the step S105, and if not, executing the step S106.
In the process of implementing step S104, it is determined whether the client risk level is greater than or equal to a preset risk level, if so, it is determined that the client risk level has a risk, and step S105 is executed, and if not, it is determined that the client risk level does not have a risk, and step S106 is executed.
It should be noted that the preset risk level is set in advance according to actual conditions, for example, the preset risk level may be set to a medium level.
S105: and outputting risk prompt information.
In the process of implementing step S105 specifically, risk prompting information is output to prompt the bank that the transaction of the customer has risk, and a corresponding risk level of the customer is displayed to the bank, so that the bank can perform corresponding processing.
S106: outputting information indicating that the customer is not at risk.
In the process of implementing step S106, information indicating that the customer is risk-free is output to prompt the bank that the customer' S transaction is risk-free, that is, the customer can proceed with the transaction.
It should be noted that the information indicating that the client does not have a risk includes a client risk level.
In the embodiment of the invention, the customer data is subjected to dimensionality reduction to determine a customer characteristic value matrix; and then, processing the client characteristic value matrix by utilizing a client grade classification model which is constructed in advance to predict the risk grade of the client so as to classify the risk grade of the client. By the method, the classification accuracy and the classification speed of the risk level of the client can be improved.
Based on the customer risk rating method shown in the above embodiment of the present invention, in the process of performing the dimension reduction processing on the customer data and determining the customer eigenvalue matrix in step S102, the method includes the following steps:
s11: and according to a preset index rule, the quantized value of the index in the client data is obtained.
In the process of implementing step S11, the quantified value of the index is extracted from various types of transaction data of the customer according to the preset index rule.
Optionally, based on the preset index rule, the method further includes:
and extracting indexes in the customer data from a preset index rule.
It should be noted that the index refers to a rule for extracting transaction information; the index feature refers to a quantized value extracted by a rule.
S12: and taking the quantized values of the indexes as client characteristic values, and combining the client characteristic values into a client characteristic value matrix.
In the process of implementing step S12, the quantized values are used as the customer feature values, and then the customer feature values are converted into column vectors, thereby forming a customer feature weight matrix.
Note that the client feature value is a feature value extracted above the index.
In the embodiment of the invention, the quantized value of the index in the client data is used as the client characteristic value according to the preset index rule, and the client characteristic value is combined into the client characteristic value matrix. And the client characteristic value matrix is processed by utilizing a client grade classification model constructed in advance so as to predict the risk grade of the client, so that the risk grade of the client is classified. By the method, the classification accuracy and the classification speed of the risk level of the client can be improved.
Optionally, based on the customer risk rating method shown in the foregoing embodiment of the present invention, after step S103 is executed and the customer eigenvalue matrix is processed based on the customer class classification model that is constructed in advance, so as to obtain a customer risk class, the method further includes the following steps:
s21: and after the client risk level is obtained, optimizing the client level classification model based on the client risk level.
In the process of implementing step S21 specifically, the network parameters of the current customer-level classification model are optimized according to the current customer eigenvalue matrix and the customer rating result corresponding to the customer eigenvalue matrix, so as to obtain a customer-level classification model constructed based on the currently optimized network parameters.
Compared with the client risk rating method shown in the embodiment of the invention, after the client characteristic value matrix is processed by using the client grade classification model, the network parameters in the current client grade classification model can be optimized according to the processed client rating result, and a new client grade classification model is further constructed. The client risk rating of the client grade classification model is more accurate.
Corresponding to the method for rating the risk of the client shown in the embodiment of the present invention, the embodiment of the present invention further discloses a schematic structural diagram of the risk rating of the client, as shown in fig. 4, the apparatus includes:
the acquiring unit 401 is configured to acquire customer data, where the customer data at least includes a transaction occurrence place, a transaction amount, a transaction date, and a transaction belonging line.
A processing unit 402, configured to perform dimension reduction processing on the client data, and determine a client eigenvalue matrix;
and a customer grade classification model 403, configured to use the customer characteristic value matrix as an input of a pre-constructed customer grade classification model, and process the customer characteristic value matrix based on the pre-constructed customer grade classification model to obtain a customer risk grade, where the pre-constructed customer grade classification model is obtained by constructing 404 with a construction unit.
And a prompting unit 405, configured to output risk prompting information when it is determined that the risk level of the client is risk.
It should be noted that, the specific principle and the implementation process of each unit in the client risk rating apparatus disclosed in the embodiment of the present application are the same as the client risk rating method described in the embodiment of the present application, and reference may be made to corresponding parts in the client risk rating method disclosed in the embodiment of the present application, and details are not repeated here.
In the embodiment of the invention, the customer data is subjected to dimensionality reduction to determine a customer characteristic value matrix; and then, processing the client characteristic value matrix by utilizing a client grade classification model which is constructed in advance to predict the risk grade of the client so as to classify the risk grade of the client. By the method, the classification accuracy and the classification speed of the risk level of the client can be improved.
Optionally, based on the client risk rating apparatus shown in the foregoing embodiment of the present invention, the constructing unit 404 includes:
the acquisition module is used for acquiring historical data, and the historical data comprises historical transaction data of customers and historical customer rating results.
And the processing module is used for performing dimensionality reduction processing on the preprocessed historical data and determining a historical customer characteristic value matrix.
And the training unit is used for training a universal neural network model based on the historical client characteristic value matrix and the historical client rating result to obtain a client grade classification model.
In an embodiment of the invention, historical data is obtained, wherein the historical data comprises historical transaction data of customers and historical customer rating results. And performing dimensionality reduction on the preprocessed historical data to determine a historical customer eigenvalue matrix. And training a universal neural network model based on the historical customer characteristic value matrix and the historical customer rating result to obtain a customer grade classification model. For subsequent rating of the risk of the customer using a customer-level classification model.
Optionally, the client risk rating apparatus shown based on the above-described embodiment of the present invention, as shown in fig. 5 in combination with fig. 4, further includes:
and an optimizing unit 406, configured to optimize the customer level classification model based on the customer risk level after obtaining the customer risk level.
In the embodiment of the invention, after the customer characteristic value matrix is processed by using the customer grade classification model, the network parameters in the current customer grade classification model can be optimized according to the processed customer grade result, and then a new customer grade classification model is constructed. The client risk rating of the client grade classification model is more accurate.
Optionally, based on the client risk rating apparatus shown in the foregoing embodiment of the present invention, the processing unit 402 is specifically configured to: according to a preset index rule, the quantized value of the index in the client data is obtained; and taking the quantized values of the indexes as client characteristic values, and combining the client characteristic values into a client characteristic value matrix.
In the embodiment of the invention, the quantized value of the index in the client data is used as the client characteristic value according to the preset index rule, and the client characteristic value is combined into the client characteristic value matrix. And the client characteristic value matrix is processed by utilizing a client grade classification model constructed in advance so as to predict the risk grade of the client, so that the risk grade of the client is classified. By the method, the classification accuracy and the classification speed of the risk level of the client can be improved.
The embodiment of the invention also discloses electronic equipment, which is used for operating the database storage process, wherein the client risk rating method disclosed by the figure 1 and the figure 2 is executed when the database storage process is operated.
The embodiment of the invention also discloses a computer storage medium, which comprises a storage database storage process, wherein when the storage database storage process runs, the equipment where the storage medium is located is controlled to execute the customer risk rating method disclosed in the above figure 1 and figure 2.
In the context of this disclosure, a computer storage medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the 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.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for rating a risk of a customer, the method comprising:
acquiring customer data, wherein the customer data at least comprises a transaction occurrence place, a transaction amount, a transaction date and a transaction affiliated line;
performing dimension reduction processing on the client data to determine a client characteristic value matrix;
the client characteristic value matrix is used as the input of a pre-constructed client grade classification model, and the client characteristic value matrix is processed based on the pre-constructed client grade classification model to obtain a client risk grade, wherein the pre-constructed client grade classification model is obtained by training through historical data;
and outputting risk prompt information when the risk level of the client is determined to have risk.
2. The method of claim 1, wherein the training with historical data to obtain a data prediction model comprises:
acquiring historical data, wherein the historical data comprises historical transaction data of customers and historical customer rating results;
performing dimensionality reduction on the preprocessed historical data to determine a historical customer eigenvalue matrix;
and training a universal neural network model based on the historical customer characteristic value matrix and the historical customer rating result to obtain a customer grade classification model.
3. The method of claim 1, further comprising:
and after the client risk level is obtained, optimizing the client level classification model based on the client risk level.
4. The method of claim 1, wherein the performing the dimension reduction on the customer data to determine a customer eigenvalue matrix comprises:
according to a preset index rule, the quantized value of the index in the client data is obtained;
and taking the quantized values of the indexes as client characteristic values, and combining the client characteristic values into a client characteristic value matrix.
5. A client risk rating apparatus, the apparatus comprising:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring customer data, and the customer data at least comprises a transaction occurrence place, a transaction amount, a transaction date and a transaction affiliated line;
the processing unit is used for performing dimensionality reduction processing on the client data and determining a client characteristic value matrix;
the client grade classification model is used for taking the client characteristic value matrix as the input of a pre-constructed client grade classification model, processing the client characteristic value matrix based on the pre-constructed client grade classification model and obtaining a client risk grade, wherein the pre-constructed client grade classification model is constructed by utilizing a construction unit;
and the prompting unit is used for outputting risk prompting information when the risk level of the client is determined to have risk.
6. The apparatus of claim 5, wherein the building unit comprises:
the acquisition module is used for acquiring historical data, wherein the historical data comprises historical transaction data of a customer and a historical customer rating result;
the processing module is used for performing dimensionality reduction processing on the preprocessed historical data and determining a historical customer eigenvalue matrix;
and the training unit is used for training a universal neural network model based on the historical client characteristic value matrix and the historical client rating result to obtain a client grade classification model.
7. The apparatus of claim 5, further comprising:
and the optimizing unit is used for optimizing the customer level classification model based on the customer risk level after obtaining the customer risk level.
8. The apparatus according to claim 5, wherein the processing unit is specifically configured to: according to a preset index rule, the quantized value of the index in the client data is obtained; and taking the quantized values of the indexes as client characteristic values, and combining the client characteristic values into a client characteristic value matrix.
9. An electronic device, characterized in that the electronic device is adapted to run a program, wherein the program when running performs the method of client risk rating according to any of claims 1-4.
10. A computer storage medium, characterized in that the storage medium comprises a stored program, wherein the program, when running, controls a device on which the storage medium is located to perform the method of client risk rating according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111037989.XA CN113744045A (en) | 2021-09-06 | 2021-09-06 | Client risk rating method and device, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111037989.XA CN113744045A (en) | 2021-09-06 | 2021-09-06 | Client risk rating method and device, electronic equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113744045A true CN113744045A (en) | 2021-12-03 |
Family
ID=78735951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111037989.XA Pending CN113744045A (en) | 2021-09-06 | 2021-09-06 | Client risk rating method and device, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113744045A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971307A (en) * | 2022-05-30 | 2022-08-30 | 中国银行股份有限公司 | Bank business efficiency monitoring method and system, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245879A (en) * | 2019-07-02 | 2019-09-17 | 中国农业银行股份有限公司 | A kind of risk rating method and device |
| CN111178767A (en) * | 2019-12-31 | 2020-05-19 | 中国银行股份有限公司 | Risk control method and system, computer device and computer-readable storage medium |
-
2021
- 2021-09-06 CN CN202111037989.XA patent/CN113744045A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245879A (en) * | 2019-07-02 | 2019-09-17 | 中国农业银行股份有限公司 | A kind of risk rating method and device |
| CN111178767A (en) * | 2019-12-31 | 2020-05-19 | 中国银行股份有限公司 | Risk control method and system, computer device and computer-readable storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971307A (en) * | 2022-05-30 | 2022-08-30 | 中国银行股份有限公司 | Bank business efficiency monitoring method and system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102044205B1 (en) | Target information prediction system using big data and machine learning and method thereof | |
| CN110400022B (en) | Cash consumption prediction method and device for self-service teller machine | |
| CN110969285B (en) | Prediction model training method, prediction device, prediction equipment and medium | |
| CN110738564A (en) | Post-loan risk assessment method and device and storage medium | |
| CN109615280A (en) | Employee's data processing method, device, computer equipment and storage medium | |
| CN108038616A (en) | A kind of work transmission line analysis of prices method | |
| CN114202243A (en) | Engineering project management risk early warning method and system based on random forest | |
| CN113344438A (en) | Loan system, loan monitoring method, loan monitoring apparatus, and loan medium for monitoring loan behavior | |
| CN113744045A (en) | Client risk rating method and device, electronic equipment and computer storage medium | |
| CN112116168A (en) | User behavior prediction method and device and electronic equipment | |
| CN116205355A (en) | Power load prediction method, device and storage medium | |
| CN113450158A (en) | Bank activity information pushing method and device | |
| CN113835947B (en) | Method and system for determining abnormality cause based on abnormality recognition result | |
| CN116843483A (en) | Vehicle insurance claim settlement method, device, computer equipment and storage medium | |
| Iefimova et al. | Methodical support of assessment of the development of economic security of the region | |
| CN109255638B (en) | Mathematical model for mining potential customers | |
| JP6588877B2 (en) | Factor analysis support device and factor analysis support method | |
| CN113421154B (en) | Credit risk assessment method and system based on control chart | |
| CN115375474A (en) | Information prompting method and device and electronic equipment | |
| KR102355255B1 (en) | A real-time stock price prediction system using LSTM neural network and text miner | |
| CN111105148B (en) | Off-job probability evaluation method, apparatus and computer readable storage medium | |
| CN114386980A (en) | Fraud identification method and device based on time sequence data driving | |
| CN112232847A (en) | Method for predicting price of complete equipment of transformer station | |
| Adekunle et al. | Capital inflows and industrial performance in Nigeria: including the excluded | |
| CN113538132B (en) | Credit scoring method, equipment and medium based on regression tree algorithm |
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 |