CN115730947A - Bank customer loss prediction method and device - Google Patents
Bank customer loss prediction method and device Download PDFInfo
- Publication number
- CN115730947A CN115730947A CN202211528615.2A CN202211528615A CN115730947A CN 115730947 A CN115730947 A CN 115730947A CN 202211528615 A CN202211528615 A CN 202211528615A CN 115730947 A CN115730947 A CN 115730947A
- Authority
- CN
- China
- Prior art keywords
- bank
- transaction data
- bank customer
- loss prediction
- testing
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a bank customer loss prediction method and a bank customer loss prediction device, which are applied to the technical field of artificial intelligence, wherein the method comprises the following steps: collecting transaction data of historical bank customers; constructing a training set and a testing set according to transaction data of historical bank customers; repeating the following training and testing processes of the machine learning model until the prediction result error of the bank customer loss prediction model is within a preset range: training the machine learning model by using a training set to obtain a bank customer loss prediction model; testing the bank customer loss prediction model by using a test set, and adjusting model parameters of the bank customer loss prediction model according to a prediction result error of the bank customer loss prediction model obtained by testing; inputting the transaction data of the bank customer to be tested into the bank customer loss prediction model, and outputting the loss prediction result of the bank customer to be tested. The invention can autonomously predict the potential loss customers of the bank, so that the bank can maintain the customers and stabilize the bank income.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a bank customer loss prediction method and device.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
In the banking system, the time, money and labor cost for developing new customers is far more than that for maintaining old customers. For the customer, the experience of different commercial banks is not very different, and the customer can switch between different banks without cost, so that the loss of old customers becomes a factor of concern in the loss of profits of the banks. There is no effective solution for bank customer churn prediction in the prior art.
Disclosure of Invention
The embodiment of the invention provides a bank customer loss prediction method, which is used for effectively realizing bank customer loss prediction and comprises the following steps:
collecting transaction data of historical bank customers;
constructing a training set and a testing set according to transaction data of historical bank customers;
repeating the following training and testing processes of the machine learning model until the prediction result error of the bank customer loss prediction model is within a preset range: training the machine learning model by using a training set to obtain a bank customer loss prediction model; testing the bank customer loss prediction model by using a test set, and adjusting model parameters of the bank customer loss prediction model according to a prediction result error of the bank customer loss prediction model obtained by testing;
inputting transaction data of the bank customer to be tested into a bank customer loss prediction model, and outputting a loss prediction result of the bank customer to be tested;
the machine learning model comprises an LSTM (Long Short Term Memory) Network and a CNN (Convolutional Neural Network), the LSTM Network is used for extracting time sequence characteristics of transaction data, the LSTM Network output is used as input data of the CNN, and the extraction of transaction data space characteristics is carried out.
The embodiment of the invention also provides a bank customer loss prediction device, which is used for effectively realizing bank customer loss prediction and comprises the following components:
the data acquisition module is used for acquiring transaction data of a historical bank customer;
the model building module is used for building a training set and a testing set according to transaction data of historical bank customers, and repeating the following training and testing processes of the machine learning model until the prediction result error of the bank customer loss prediction model is within a preset range: training the machine learning network by using a training set to obtain a bank customer loss prediction model; testing the bank customer loss prediction model by using a test set, and adjusting model parameters of the bank customer loss prediction model according to a prediction result error of the bank customer loss prediction model obtained by testing;
the loss prediction module is used for inputting transaction data of the bank customer to be tested into the bank customer loss prediction model and outputting a loss prediction result of the bank customer to be tested;
the machine learning model comprises an LSTM network and a CNN, and the LSTM network is used for extracting time sequence characteristics of transaction data, the LSTM network is used for outputting input data serving as the CNN, and the extraction of transaction data space characteristics is carried out.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the bank customer churn prediction method.
The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and when the computer program is executed by a processor, the bank customer churn prediction method is realized.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when executed by a processor, the computer program implements the bank customer churn prediction method.
In the embodiment of the invention, transaction data of a historical bank client is collected, and a training set and a test set are constructed according to the transaction data of the historical bank client; repeating the following training and testing processes of the machine learning model until the prediction result error of the bank customer loss prediction model is within a preset range: training the machine learning model by using a training set to obtain a bank customer loss prediction model; testing the bank customer loss prediction model by using a test set, and adjusting model parameters of the bank customer loss prediction model according to a prediction result error of the bank customer loss prediction model obtained by testing; inputting transaction data of the bank customer to be tested into a bank customer loss prediction model, and outputting a loss prediction result of the bank customer to be tested; therefore, bank customer loss prediction is effectively realized; the machine learning model comprises an LSTM network and a CNN, wherein the LSTM network is used for extracting the time sequence characteristics of transaction data, the LSTM network is used for outputting the time sequence characteristics as input data of the CNN, and the extraction of the transaction data space characteristics is carried out.
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 embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts. In the drawings:
FIG. 1 is a flow chart of a bank customer churn prediction method in accordance with an embodiment of the present invention;
FIG. 2 is an exemplary diagram of training set and test set construction in an embodiment of the present invention;
FIG. 3 is an exemplary diagram of training and testing of a machine learning model in an embodiment of the present invention;
FIG. 4 is a data flow diagram of model training in an embodiment of the present invention;
FIG. 5 is a diagram illustrating an exemplary embodiment of an apparatus for predicting bank customer churn;
FIG. 6 is a diagram of an embodiment of a bank customer churn prediction device according to the present invention;
FIG. 7 is a diagram of a computer device in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
In the description of the present specification, the terms "comprising," "including," "having," "containing," and the like are used in an open-ended fashion, i.e., to mean including, but not limited to. Reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The sequence of steps involved in the various embodiments is provided to schematically illustrate the practice of the invention, and the sequence of steps is not limited and can be suitably adjusted as desired.
In order to solve the technical problems in the prior art, the invention provides a bank customer loss prediction method which is used for realizing the prediction of bank customer loss in advance, reducing the risk of profit reduction, improving the prediction accuracy and better knowing the potential intention of customers. Fig. 1 is a flowchart of a bank customer churn prediction method according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
102, constructing a training set and a testing set according to transaction data of a historical bank customer;
and step 104, inputting the transaction data of the bank user to be tested into the bank customer loss prediction model, and outputting the loss prediction result of the bank user to be tested.
As can be seen from the flow shown in fig. 1, the embodiment of the present invention can effectively implement the bank customer churn prediction; the machine learning model comprises an LSTM network and a CNN, wherein the LSTM network is used for extracting the time sequence characteristics of transaction data, the LSTM network is used for outputting the time sequence characteristics as input data of the CNN, and the extraction of the transaction data space characteristics is carried out.
During specific implementation, transaction data of historical bank customers can be collected; and constructing a training set and a testing set according to the transaction data of the historical bank customers.
In one embodiment, the transaction data includes: the transaction flow, the contract signing information of the bank products, the use information of the bank products and the like or any combination thereof.
In one embodiment, the influence of customers on bank income is analyzed, large customers with large transaction amount can generate high influence on bank income, a threshold value is set according to the influence of customers on bank income, the large customers with the transaction amount exceeding the threshold value are used as a main data source, and scattered customers with small transaction amount are screened out.
In one embodiment, the transaction data of the historical bank customers with transaction amount larger than a threshold value is screened out according to the transaction data of the historical bank customers; constructing a training set and a testing set according to the screened transaction data of the historical bank customers; for example, 80% of the transaction data may be randomly drawn as a training set for training the machine learning model, and the remaining 20% of the transaction data may be drawn as a test set for predicting accuracy of the machine learning model.
Fig. 2 is a diagram of a specific example of constructing a training set and a test set in an embodiment of the present invention, and as shown in fig. 2, in an embodiment of the present invention, constructing a training set and a test set may include:
and step 203, constructing a training set and a testing set according to the screened data.
In one embodiment, the transaction data of the historical bank customers are sorted according to the transaction time to form a time sequence; the transaction data is divided into time series with different characteristics according to the customer behaviors, and a training set and a testing set are constructed according to the time series.
In an embodiment, the time series of different features may include, for example: the transaction flow, the activated bank product quantity and the contracted bank product quantity form a time sequence.
The prediction of customer churn is generally regarded as a classification prediction problem, the time sequence characteristic displayed by data enables time sequence prediction to be possible, and the LSTM network is taken as a popular model in the time sequence prediction problem and can well capture the time characteristic of the data, but the single LSTM network cannot analyze more complex customer characteristic and cannot understand customer behavior. In the embodiment of the invention, while the LSTM network is used, the CNN is added, so as to analyze more complex spatial features in the data, and achieve higher prediction accuracy. CNN, although more used for image recognition tasks, has a significant effect on temporal prediction.
In specific implementation, the following training and testing processes of the machine learning model can be repeated until the prediction result error of the bank customer loss prediction model is within a preset range: training the machine learning model by using a training set to obtain a bank customer loss prediction model; and testing the bank customer loss prediction model by using the test set, and adjusting model parameters of the bank customer loss prediction model according to the prediction result error of the bank customer loss prediction model obtained by testing.
Fig. 3 is a diagram of an embodiment of training and testing a machine learning model according to the present invention, and as shown in fig. 3, in an embodiment of the present invention, the training and testing of the machine model may include:
and step 304, adjusting model parameters, and repeating the steps 301 to 303 until the prediction accuracy is in a specified range.
In the embodiment of the invention, the machine learning model comprises an LSTM network and a CNN, wherein the LSTM network is used for processing sequence data, can learn long-term dependency relationship and uses the previous data in the processing of the current task; CNNs are propagated back through multiple layers of construction, enabling the algorithm to autonomously learn the spatial characteristics of the data adaptively.
In one embodiment, in the machine learning model, input data sequentially pass through an input layer, an LSTM network and a CNN, and a prediction result is output; the LSTM network output sequentially passes through the CNN convolutional layer, the CNN pooling layer and the CNN full-connection layer, and a prediction result is output.
Fig. 4 is a data flow diagram of model training in the embodiment of the present invention, and as shown in fig. 4, in the embodiment of the present invention, the data flow of model training is:
401, reading customer transaction data by the model, and entering the customer transaction data into an input layer;
402, the input layer transmits the customer transaction data into the LSTM network for processing;
403, the LSTM network processes the customer transaction data, and transmits the processed customer transaction data with time sequence characteristics into the CNN convolutional layer for processing;
404, processing the customer transaction data with data characteristics by the CNN convolutional layer, and transmitting the processed customer transaction data into the CNN pooling layer;
405, the CNN pooling layer transmits the processed customer transaction data with the spatial characteristics into a CNN full link layer to obtain a prediction result;
406, the CNN full link layer transmits the prediction result to the output layer, and outputs the prediction result.
In one embodiment, a cross-validation approach is used to test bank customer churn prediction models using a test set.
In the embodiment of the invention, the LSTN network is used for analyzing the transaction data time sequence characteristics, the CNN is added for analyzing the transaction data space characteristics user behaviors, the LSTM network and the CNN are used in combination, the capability of acquiring the data characteristics by an algorithm is improved, the data time sequence characteristics and some potential space characteristics which are difficult to analyze and summarize manually are included, the accuracy of customer loss prediction is improved, the machine learning method is applied to a bank customer maintenance scene, the output of manpower is greatly reduced, the manpower and time cost are reduced, the commercial bank is better helped to maintain old customers, and the profit and the income of the bank are stabilized.
In one embodiment, transaction data of a bank user to be tested is input into a bank client loss prediction model, a loss prediction result of the bank client to be tested is output, and when the loss prediction result of the bank client to be tested is that loss risk exists, early warning information is sent out to remind a bank party to take measures to save the client.
The embodiment of the invention also provides a bank customer churn prediction device, which is described in the following embodiment. Because the principle of solving the problems of the device is similar to the bank customer churn prediction method, the implementation of the device can refer to the implementation of the method, and repeated parts are not described again.
Fig. 5 is a schematic diagram of a bank customer churn prediction device according to an embodiment of the present invention, as shown in fig. 5, the device includes:
the data acquisition module 501 is used for acquiring transaction data of historical bank customers;
the model building module 502 is configured to build a training set and a testing set according to transaction data of a historical bank customer, and repeat the following training and testing processes of the machine learning model until a prediction result error of the bank customer loss prediction model is within a preset range: training the machine learning network by using a training set to obtain a bank customer loss prediction model; testing the bank customer loss prediction model by using a test set, and adjusting model parameters of the bank customer loss prediction model according to a prediction result error of the bank customer loss prediction model obtained by testing;
the loss prediction module 503 is configured to input transaction data of the bank customer to be tested into the bank customer loss prediction model, and output a loss prediction result of the bank customer to be tested;
the machine learning model comprises an LSTM network and a CNN, and the LSTM network is used for extracting time sequence characteristics of transaction data, the LSTM network is used for outputting input data serving as the CNN, and the extraction of transaction data space characteristics is carried out.
In one embodiment, the transaction data may include: the transaction flow, the contract signing information of the bank products and the use information of the bank products are one or any combination.
In an embodiment, model building module 502 may be specifically configured to:
screening out transaction data of the historical bank customers with transaction amount larger than a threshold value according to the transaction data of the historical bank customers;
and constructing a training set and a testing set according to the screened transaction data of the historical bank customers.
In an embodiment, model building module 502 may be specifically configured to:
according to the transaction time, sequencing the transaction data of the historical bank customers to form a time sequence; wherein the transaction data is divided into a time series of different characteristics based on the customer behavior;
and constructing a training set and a testing set according to the time sequence.
In an embodiment, the time series of different features may include: the method comprises the steps of obtaining a time sequence consisting of transaction running water, the number of activated bank products and the number of contracted bank products.
In one embodiment, in the machine learning model, input data sequentially pass through an input layer, an LSTM network and a CNN, and a prediction result is output; the LSTM network output sequentially passes through the CNN convolutional layer, the CNN pooling layer and the CNN full-connection layer, and a prediction result is output.
In an embodiment, model building module 502 may be specifically configured to:
and testing the bank customer loss prediction model by using a test set in a cross validation mode.
Fig. 6 is a diagram illustrating an embodiment of a bank customer churn prediction apparatus according to the present invention, and as shown in fig. 6, in the embodiment of the present invention, the bank customer churn prediction apparatus shown in fig. 5 may further include:
and the early warning module 601 is configured to send early warning information when the loss prediction result of the bank customer to be tested output by the loss prediction module indicates that a loss risk exists.
Fig. 7 is a schematic diagram of a computer device according to an embodiment of the present invention, where the computer device 700 includes a memory 710, a processor 720, and a computer program 730 stored in the memory 710 and executable on the processor 720, and when the processor 720 executes the computer program 730, the bank customer churn prediction method is implemented.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the bank customer churn prediction method is realized.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when executed by a processor, the computer program implements the bank customer churn prediction method.
In summary, in the embodiment of the present invention, a training set and a test set are constructed by collecting transaction data of a historical bank customer according to the transaction data of the historical bank customer; repeating the following training and testing processes of the machine learning model until the prediction result error of the bank customer loss prediction model is within a preset range: training the machine learning model by using a training set to obtain a bank customer loss prediction model; testing the bank customer loss prediction model by using a test set, and adjusting model parameters of the bank customer loss prediction model according to a prediction result error of the bank customer loss prediction model obtained by testing; inputting transaction data of the bank customer to be tested into a bank customer loss prediction model, and outputting a loss prediction result of the bank customer to be tested; therefore, bank customer loss prediction is effectively realized; the machine learning model comprises an LSTM network and a CNN, wherein the LSTM network is used for extracting the time sequence characteristics of transaction data, the LSTM network is used for outputting the time sequence characteristics as input data of the CNN, and the extraction of the transaction data space characteristics is carried out.
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 has been 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 flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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 means 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 instruction means 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.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (19)
1. A bank customer churn prediction method is characterized by comprising the following steps:
collecting transaction data of historical bank customers;
constructing a training set and a testing set according to transaction data of historical bank customers;
repeating the following training and testing processes of the machine learning model until the prediction result error of the bank customer loss prediction model is within a preset range: training the machine learning model by using a training set to obtain a bank customer loss prediction model; testing the bank customer loss prediction model by using the test set, and adjusting model parameters of the bank customer loss prediction model according to a prediction result error of the bank customer loss prediction model obtained by testing;
inputting transaction data of the bank customer to be tested into a bank customer loss prediction model, and outputting a loss prediction result of the bank customer to be tested;
the machine learning model comprises a long-short term memory (LSTM) network and a Convolutional Neural Network (CNN), the LSTM network is used for extracting time sequence characteristics of transaction data, the output of the LSTM network is used as input data of the CNN, and the extraction of transaction data space characteristics is carried out.
2. The method of claim 1, wherein the transaction data comprises: the transaction flow, the contract signing information of the bank products and the use information of the bank products are one or any combination.
3. The method of claim 1, wherein constructing a training set and a test set from historical bank customer transaction data comprises:
screening out transaction data of the historical bank customers with transaction amount larger than a threshold value according to the transaction data of the historical bank customers;
and constructing a training set and a testing set according to the screened transaction data of the historical bank customers.
4. The method of claim 1, wherein building a training set and a testing set from historical bank customer transaction data further comprises:
according to the transaction time, sorting the transaction data of the historical bank customers to form a time sequence; wherein the transaction data is divided into a time series of different characteristics based on the customer behavior;
and constructing a training set and a testing set according to the time sequence.
5. The method of claim 3, wherein the time series of different features comprises: the method comprises the steps of obtaining a time sequence consisting of transaction running water, the number of activated bank products and the number of contracted bank products.
6. The method of claim 1, wherein in the machine learning model, input data sequentially passes through an input layer, an LSTM network and a CNN, and a prediction result is output; the LSTM network output sequentially passes through the CNN convolutional layer, the CNN pooling layer and the CNN full-connection layer, and a prediction result is output.
7. The method of claim 1, wherein testing the bank customer churn prediction model using a test set comprises:
and testing the bank customer loss prediction model by using a test set in a cross validation mode.
8. The method of claim 1, further comprising:
and when the loss prediction result of the bank customer to be detected is that loss risk exists, sending out early warning information.
9. A bank customer churn prediction device, comprising:
the data acquisition module is used for acquiring transaction data of historical bank customers;
the model building module is used for building a training set and a testing set according to transaction data of historical bank customers, and repeating the following training and testing processes of the machine learning model until the prediction result error of the bank customer loss prediction model is within a preset range: training the machine learning network by using a training set to obtain a bank customer loss prediction model; testing the bank customer loss prediction model by using the test set, and adjusting model parameters of the bank customer loss prediction model according to a prediction result error of the bank customer loss prediction model obtained by testing;
the loss prediction module is used for inputting the transaction data of the bank customer to be tested into the bank customer loss prediction model and outputting the loss prediction result of the bank customer to be tested;
the machine learning model comprises an LSTM network and a CNN, the LSTM network is used for extracting time sequence characteristics of transaction data, the LSTM network is used for outputting input data serving as the CNN, and the transaction data space characteristics are extracted.
10. The apparatus of claim 9, wherein the transaction data comprises: the transaction flow, the contract signing information of the bank product, the use information of the bank product or any combination thereof.
11. The apparatus of claim 9, wherein the model building module is specifically configured to:
screening out transaction data of the historical bank customers with transaction amount larger than a threshold value according to the transaction data of the historical bank customers;
and constructing a training set and a testing set according to the screened transaction data of the historical bank customers.
12. The apparatus of claim 9, wherein the model building module is specifically configured to:
according to the transaction time, sequencing the transaction data of the historical bank customers to form a time sequence; wherein the transaction data is divided into a time series of different characteristics based on the customer behavior;
and constructing a training set and a testing set according to the time sequence.
13. The apparatus of claim 11, wherein the time series of different features comprises: the transaction flow, the activated bank product quantity and the contracted bank product quantity form a time sequence.
14. The apparatus of claim 9, wherein in the machine learning model, input data sequentially passes through an input layer, an LSTM network, and a CNN, and a prediction result is output; the LSTM network output sequentially passes through the CNN convolutional layer, the CNN pooling layer and the CNN full-connection layer, and a prediction result is output.
15. The apparatus of claim 9, wherein the model building module is specifically configured to:
and testing the bank customer loss prediction model by using a test set in a cross validation mode.
16. The apparatus of claim 9, further comprising:
and the early warning module is used for sending out early warning information when the loss prediction result of the bank customer to be detected, which is output by the loss prediction module, is that loss risk exists.
17. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 8 when executing the computer program.
18. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 8.
19. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211528615.2A CN115730947A (en) | 2022-11-30 | 2022-11-30 | Bank customer loss prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211528615.2A CN115730947A (en) | 2022-11-30 | 2022-11-30 | Bank customer loss prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115730947A true CN115730947A (en) | 2023-03-03 |
Family
ID=85299686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211528615.2A Pending CN115730947A (en) | 2022-11-30 | 2022-11-30 | Bank customer loss prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115730947A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664184A (en) * | 2023-07-31 | 2023-08-29 | 广东南方电信规划咨询设计院有限公司 | Client loss prediction method and device based on federal learning |
| CN117422181A (en) * | 2023-12-15 | 2024-01-19 | 湖南三湘银行股份有限公司 | Fuzzy label-based method and system for early warning loss of issuing clients |
-
2022
- 2022-11-30 CN CN202211528615.2A patent/CN115730947A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664184A (en) * | 2023-07-31 | 2023-08-29 | 广东南方电信规划咨询设计院有限公司 | Client loss prediction method and device based on federal learning |
| CN116664184B (en) * | 2023-07-31 | 2024-01-12 | 广东南方电信规划咨询设计院有限公司 | Client loss prediction method and device based on federal learning |
| CN117422181A (en) * | 2023-12-15 | 2024-01-19 | 湖南三湘银行股份有限公司 | Fuzzy label-based method and system for early warning loss of issuing clients |
| CN117422181B (en) * | 2023-12-15 | 2024-04-02 | 湖南三湘银行股份有限公司 | Fuzzy label-based method and system for early warning loss of issuing clients |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111124840B (en) | Method and device for predicting alarm in business operation and maintenance and electronic equipment | |
| CN110009171B (en) | User behavior simulation method, device, equipment and computer readable storage medium | |
| CN115730947A (en) | Bank customer loss prediction method and device | |
| CN111768008A (en) | Federal learning method, device, equipment and storage medium | |
| CN111178523A (en) | Behavior detection method and device, electronic equipment and storage medium | |
| CN110738564A (en) | Post-loan risk assessment method and device and storage medium | |
| CN110910982A (en) | Self-coding model training method, device, equipment and storage medium | |
| CN111369299A (en) | Method, device and equipment for identification and computer readable storage medium | |
| CN109815855B (en) | Electronic equipment automatic test method and system based on machine learning | |
| CN111932367A (en) | Pre-credit evaluation method and device | |
| CN116091185A (en) | Customer loss early warning method and device | |
| CN109242165A (en) | A kind of model training and prediction technique and device based on model training | |
| Ackermann et al. | Black-box learning of parametric dependencies for performance models | |
| CN112257332B (en) | Simulation model evaluation method and device | |
| CN116775741A (en) | Auditing method and related device for completion resolution of engineering | |
| CN110910241A (en) | Cash flow evaluation method, apparatus, server device and storage medium | |
| CN114548307A (en) | Classification model training method and device, and classification method and device | |
| CN111680572B (en) | Dynamic judgment method and system for power grid operation scene | |
| Hashemi et al. | Runtime monitoring for out-of-distribution detection in object detection neural networks | |
| CN111815442B (en) | Link prediction method and device and electronic equipment | |
| CN111667107B (en) | Research and development management and control problem prediction method and device based on gradient random forest | |
| CN116636815B (en) | Electroencephalogram signal-based sleeping quality assessment method and system for underwater operators | |
| KR102512552B1 (en) | Apparatus and method for analyzing artificial intelligence processing results | |
| CN115439221A (en) | Bank customer data analysis method and device | |
| CN117874491A (en) | Feature extraction method and device |
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 |