Methods, apparatus, storage media and electronic devices for determining target objects

Abstract

This application discloses a method, apparatus, storage medium, and electronic device for determining target objects, relating to the field of financial technology. The method includes: acquiring feature data of multiple target objects for at least one credit card product to be predicted; inputting the feature data of multiple target objects for each credit card product into a regression model corresponding to each credit card product for prediction, obtaining a prediction label distribution for each credit card product, wherein the prediction label distribution is a probability distribution representing the activity status of the target objects with respect to the credit card product; and determining the target object for each credit card product from the multiple target objects for each credit card product based on the prediction label distribution. This application solves the technical problem of low accuracy in identifying inactive customers of credit card products in existing technologies.

Description

Technical Field

[0001] This application relates to the field of financial technology, and more specifically, to a method, apparatus, storage medium, and electronic device for determining a target object. Background Technology

[0002] Many credit card customers use their cards infrequently after activation, resulting in few transactions or information updates within a certain timeframe. Over time, this leads banks to convert these customers into inactive accounts, thus losing a group of potential card users. Therefore, it is necessary to predict inactive accounts. Currently, existing technologies have relatively low accuracy in identifying inactive customers for credit card products.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, storage medium, and electronic device for determining a target object, so as to at least solve the technical problem of low accuracy in identifying inactive customers of credit card products in the prior art.

[0005] To achieve the above objectives, according to one aspect of this application, a method for determining a target object is provided, comprising: acquiring feature data of multiple objects to be predicted for at least one credit card product; inputting the feature data of multiple objects to be predicted for each credit card product into a regression model corresponding to each credit card product for prediction, thereby obtaining a prediction label distribution for each credit card product, wherein the prediction label distribution is a probability distribution representing the activity status of the objects to be predicted in relation to the credit card product; and determining the target object of each credit card product from the multiple objects to be predicted for each credit card product based on the prediction label distribution.

[0006] Furthermore, based on the predicted label distribution, the target object of each credit card product is determined from multiple objects to be predicted for each credit card product, including: comparing the probability value corresponding to each object to be predicted in the predicted label distribution with a preset threshold; and selecting the object to be predicted with a probability value greater than the preset threshold from among the multiple objects to be predicted as the target object.

[0007] Further, the regression model for each credit card product is obtained through the following steps: Historical card usage data for each credit card product is acquired and vectorized to obtain a card usage feature vector for each product; a discrete Gaussian distribution is constructed based on the card usage feature vector for each product to obtain a labeled distribution for each product; based on the labeled distribution for each product, independent and dependent variable matrices are constructed, and an initial regression model is established using partial least squares (PLS) based on these matrices. The independent variable matrix represents the feature information of all credit card products, and the dependent variable matrix represents the activity information of the sample objects for each credit card product; based on the initial regression model, adaptive standard deviation adjustment is performed on each credit card product to obtain the regression model for each product.

[0008] Furthermore, based on the independent variable matrix and the dependent variable matrix, a partial least squares method is used to establish an initial regression model, including: constructing a linear dependency relationship between the independent variable matrix and the dependent variable matrix; based on the linear dependency relationship, extracting multiple pairs of latent variables that are related to the independent and dependent variables, and maximizing the covariance among the latent variables to obtain the initial regression model.

[0009] Furthermore, based on the initial regression model, adaptive standard deviation adjustment is performed on each credit card product to obtain the regression model corresponding to each credit card product. This includes: configuring a first standard deviation for each credit card product, and determining the initial label distribution corresponding to each credit card product based on the first standard deviation and the label distribution corresponding to each credit card product; determining the predicted label distribution corresponding to each credit card product based on the initial regression model, and determining the target standard deviation corresponding to each credit card product based on the initial label distribution and the predicted label distribution corresponding to each credit card product; updating the initial regression model based on the target standard deviation corresponding to each credit card product to obtain the regression model corresponding to each credit card product.

[0010] Furthermore, based on the initial label distribution and the predicted label distribution corresponding to each credit card product, the target standard deviation corresponding to each credit card product is determined, including: performing similarity calculation on the initial label distribution and the predicted label distribution corresponding to each credit card product to obtain the calculation result; optimizing the first standard deviation with the goal of minimizing the calculation result to obtain the target standard deviation corresponding to each credit card product.

[0011] Furthermore, after determining the target object of each credit card product from multiple predictable objects for each credit card product, the method further includes: sending a reminder message to the target object of each credit card product, wherein the reminder message is used to remind the target object of card usage.

[0012] To achieve the above objectives, according to another aspect of this application, a target object determination apparatus is also provided, comprising: a first acquisition unit, configured to acquire feature data of multiple objects to be predicted for at least one credit card product; a first processing unit, configured to input the feature data of multiple objects to be predicted for each credit card product into a regression model corresponding to each credit card product for prediction, thereby obtaining a prediction label distribution corresponding to each credit card product, wherein the prediction label distribution is a probability distribution representing the activity state of the objects to be predicted in relation to the credit card product; and a determination unit, configured to determine the target object of each credit card product from the multiple objects to be predicted for each credit card product based on the prediction label distribution.

[0013] Furthermore, the determining unit includes: a comparison subunit, used to compare the probability value corresponding to each object to be predicted in the prediction label distribution with a preset threshold; and a determining subunit, used to select the object to be predicted among multiple objects to be predicted whose probability value is greater than the preset threshold as the target object.

[0014] Furthermore, the device also includes the following units for obtaining a regression model corresponding to each credit card product through the following steps: a second acquisition unit for acquiring historical card usage data corresponding to each credit card product and vectorizing the historical card usage data to obtain a card usage feature vector corresponding to each credit card product; a second processing unit for constructing a discrete Gaussian distribution based on the card usage feature vector corresponding to each credit card product to obtain a labeled distribution corresponding to each credit card product; a third processing unit for constructing an independent variable matrix and a dependent variable matrix based on the labeled distribution corresponding to each credit card product, and establishing an initial regression model using partial least squares method based on the independent variable matrix and the dependent variable matrix, wherein the independent variable matrix is ​​used to represent the feature information of all credit card products, and the dependent variable matrix is ​​used to represent the activity information of the sample object for each credit card product; and a fourth processing unit for adaptively adjusting the standard deviation of each credit card product based on the initial regression model to obtain a regression model corresponding to each credit card product.

[0015] Furthermore, the third processing unit includes: a first processing subunit for constructing the linear dependency relationship between the independent variable matrix and the dependent variable matrix; and a second processing subunit for extracting multiple pairs of latent variables related to the independent and dependent variables based on the linear dependency relationship, and maximizing the covariance between the latent variables to obtain the initial regression model.

[0016] Furthermore, the fourth processing unit includes: a third processing subunit, used to configure a first standard deviation for each credit card product, and determine the initial label distribution corresponding to each credit card product based on the first standard deviation and the label distribution corresponding to each credit card product; a fourth processing subunit, used to determine the predicted label distribution corresponding to each credit card product based on the initial regression model, and determine the target standard deviation corresponding to each credit card product based on the initial label distribution and the predicted label distribution corresponding to each credit card product; and a fifth processing subunit, used to update the initial regression model based on the target standard deviation corresponding to each credit card product to obtain the regression model corresponding to each credit card product.

[0017] Furthermore, the fourth processing subunit includes: a calculation module, used to perform similarity calculation on the initial label distribution and the predicted label distribution corresponding to each credit card product to obtain the calculation result; and a processing module, used to optimize the first standard deviation with the goal of minimizing the calculation result to obtain the target standard deviation corresponding to each credit card product.

[0018] Furthermore, the device also includes a sending unit, configured to send a prompt message to each target object of a credit card product after determining the target object of each credit card product from multiple predictable objects of each credit card product, wherein the prompt message is used to remind the target object of card usage.

[0019] To achieve the above objectives, according to another aspect of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the above-described method for determining the target object.

[0020] To achieve the above objectives, according to another aspect of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, which is configured to execute the above-described method for determining the target object at runtime.

[0021] To achieve the above objectives, according to another aspect of this application, an electronic device is also provided, comprising one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are configured to run the programs, wherein the programs are configured to execute the above-described method for determining the target object during runtime.

[0022] In this embodiment, a label distribution learning algorithm based on multiple multivariate regression is used for modeling. First, feature data of multiple predictable objects for at least one credit card product to be predicted are obtained. Then, the feature data of multiple predictable objects for each credit card product are input into the regression model corresponding to each credit card product for prediction, resulting in a predicted label distribution for each credit card product. This predicted label distribution represents the probability distribution of the predictable object's activity status with respect to the credit card product. Based on the predicted label distribution, the target object for each credit card product is determined from the multiple predictable objects. By establishing an adaptive inactive customer prediction model for each credit card product, inactive customer groups can be screened out for each product, accurately identifying customers who may become inactive credit card customers in the future. This achieves the goal of precisely reactivating inactive credit card customers, thereby improving accuracy and solving the technical problem of low accuracy in identifying inactive credit card customers in existing technologies. Attached Figure Description

[0023] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0024] Figure 1 This is a flowchart of an optional method for determining a target object according to an embodiment of this application;

[0025] Figure 2 This is a schematic diagram of an optional marker distribution according to an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of an optional target object determination device according to an embodiment of this application;

[0027] Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding access points are provided for users to choose to authorize or refuse. For example, interfaces are set up between this system and relevant users or organizations, providing users with corresponding access points to choose to agree to or refuse automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0031] Example 1

[0032] According to an embodiment of this application, an embodiment of a method for determining a target object is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0033] Figure 1 This is a flowchart of an optional method for determining a target object according to an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:

[0034] Step S101: Obtain feature data of multiple objects to be predicted for at least one credit card product to be predicted.

[0035] In the above steps, application systems, processors, electronic devices, etc., can be used as the execution subject. Optionally, the target object determination system can be used as the execution subject. First, feature data of multiple objects to be predicted for at least one credit card product are acquired. This feature data may include card opening date, card level, card limit, cardholder credit rating, credit card spending amount, number of credit card transactions, credit card installment period, and credit card installment amount. Optionally, the feature data may undergo data preprocessing such as standardization or centralization to ensure that the data format is consistent with that used during model training, facilitating direct application of the model.

[0036] Step S102: Input the feature data of multiple objects to be predicted for each credit card product into the regression model corresponding to each credit card product for prediction, and obtain the prediction label distribution corresponding to each credit card product. The prediction label distribution is the probability distribution representing the activity status of the objects to be predicted in relation to the credit card product.

[0037] Step S103: Based on the predicted label distribution, determine the target object of each credit card product from multiple objects to be predicted for each credit card product.

[0038] Optionally, the feature data of multiple targets to be predicted for each credit card product can be input into the regression model corresponding to each credit card product for prediction. The model can calculate the customer's activity level prediction for the credit card product based on the regression coefficients and the linear relationship between the independent and dependent variables, thus obtaining the prediction label distribution for each credit card product. Then, based on the prediction label distribution, the target object of each credit card product can be determined from the multiple targets to be predicted for each credit card product. That is, based on this distribution, it is possible to identify which customer is most likely to become an inactive account for each credit card product, i.e., to find the label with the lowest descriptiveness. This can help the bank accurately identify which customers have a higher risk of inactive accounts and then take corresponding reactivation strategies to improve the activity of these customers.

[0039] Based on the scheme defined in steps S101 to S103 above, it can be understood that in this embodiment, a label distribution learning algorithm based on multiple multivariate regression is used for modeling. First, feature data of multiple objects to be predicted for at least one credit card product are obtained. Then, the feature data of multiple objects to be predicted for each credit card product are input into the regression model corresponding to each credit card product for prediction, resulting in a predicted label distribution for each credit card product. The predicted label distribution represents the probability distribution of the activity status of the objects to be predicted in relation to the credit card product. Then, based on the predicted label distribution, the target object of each credit card product is determined from the multiple objects to be predicted for each credit card product. By establishing an adaptive inactive customer prediction model for each credit card product, inactive customer groups can be screened out for each credit card product, accurately locating customers who may become inactive credit card customers in the future. This achieves the goal of accurately reactivating inactive credit card customers, thereby improving the technical effect of accuracy and solving the technical problem of low accuracy in identifying inactive customers of credit card products in the prior art.

[0040] In one optional embodiment, the target object of each credit card product is determined from multiple objects to be predicted for each credit card product based on the predicted label distribution, including: comparing the probability value corresponding to each object to be predicted in the predicted label distribution with a preset threshold; and selecting the object to be predicted from the multiple objects to be predicted whose probability value is greater than the preset threshold as the target object.

[0041] Optionally, a threshold is set to determine whether a customer is marked as inactive. For example, if the predicted probability is less than the threshold, the customer is marked as active; if it is greater than the threshold, the customer is marked as inactive. Therefore, the probability value corresponding to each object to be predicted in the predicted label distribution is compared with the preset threshold, and the object to be predicted with a probability value greater than the preset threshold among multiple objects to be predicted is taken as the target object.

[0042] It should be noted that by comparing the probability value corresponding to each object to be predicted in the predicted label distribution with a preset threshold, it is possible to screen out inactive customer groups for each credit card product and accurately locate customers who may become inactive credit card users in the future.

[0043] In one optional embodiment, the regression model for each credit card product is obtained through the following steps: acquiring historical card usage data for each credit card product and vectorizing the historical card usage data to obtain a card usage feature vector for each credit card product; constructing a discrete Gaussian distribution based on the card usage feature vector for each credit card product to obtain a labeled distribution for each credit card product; constructing an independent variable matrix and a dependent variable matrix based on the labeled distribution for each credit card product, and establishing an initial regression model using partial least squares based on the independent variable matrix and the dependent variable matrix, wherein the independent variable matrix is ​​used to represent the feature information of all credit card products, and the dependent variable matrix is ​​used to represent the activity information of the sample object for each credit card product; and adjusting the standard deviation for each credit card product based on the initial regression model to obtain the regression model for each credit card product.

[0044] Optionally, constructing a regression model for each credit card product mainly includes feature extraction, label distribution, multiple regression learning, and adaptive model adjustment. First, feature extraction is performed to obtain historical card usage data for each credit card product, and this historical data is vectorized to obtain a usage feature vector for each credit card product. Specifically, historical card usage data is obtained from the data lake containing data on credit card products and cardholder usage, and then vectorized. This allows for the unified extraction of usage feature values ​​for all cardholders under the same credit card product (e.g., card opening date, card level, card limit, cardholder credit rating, credit card spending amount, number of credit card transactions, number of installment periods, installment amount, etc.) and feature values ​​for all credit card products (e.g., card issuance date, issuing region, card fees, etc.), establishing a one-to-many relationship between credit card products and customers.

[0045] Furthermore, a discrete Gaussian distribution is constructed based on the card usage feature vector corresponding to each credit card product, resulting in the label distribution for each credit card product. Specifically, the credit card product is considered as instance x, and the cardholder's card usage features are considered as labels w. Each possible label covered by instance x is represented as w. In the label distribution of instance x, each label w is assigned a real number y. x,w , where y x,w Let ∈[0,1], representing the descriptive degree of label w for instance x. Add the descriptive degrees of all possible labels w for instance x, assuming the sum always equals 1, i.e., ∑ w y x,w =1, which means that all labels in the label set of instance x can completely describe instance x. A discrete Gaussian distribution N(α, σ) is chosen. 2 Let be the labeled distribution of credit card product x, where the mean is cardholder usage characteristic α and the standard deviation is σ, expressed by the following formula:

[0046]

[0047] The normalization factor Z is represented as follows:

[0048]

[0049] Figure 2 This is a schematic diagram of an optional marker distribution according to an embodiment of this application, such as... Figure 2 As shown, the discrete Gaussian distribution of cardholder usage characteristics α for credit card products is presented.

[0050] Furthermore, multiple regression learning is performed, that is, based on the label distribution corresponding to each credit card product, an independent variable matrix and a dependent variable matrix are constructed, and based on the independent variable matrix and the dependent variable matrix, a partial least squares method is used to establish an initial regression model (i.e. a unified customer activity prediction model).

[0051] In one optional embodiment, an initial regression model is established using partial least squares method based on the independent variable matrix and the dependent variable matrix, including: constructing a linear dependency relationship between the independent variable matrix and the dependent variable matrix; based on the linear dependency relationship, extracting multiple pairs of latent variables related to the independent and dependent variables, and maximizing the covariance among the latent variables to obtain the initial regression model.

[0052] Optionally, a linear dependency relationship between the independent and dependent variable matrices is first constructed. Then, based on this linear dependency, multiple pairs of latent variables related to the independent and dependent variables are extracted, and the covariance among the latent variables is maximized to obtain the initial regression model. Specifically, it is assumed that the feature space of all credit card products is represented as X∈R. n×d The finite set of all credit card customers is represented as w = {w1, w2, ..., w...} c Given a training set S = {(x1, α1), (x2, α2), ..., (x...}. n ,α n )}, where the feature vector of the i-th credit card product is represented as x i ∈X, x i The customer is represented as α i ∈w. x i The corresponding generated label distribution y i =N(α) i ,σ 2 The formula is as follows:

[0053]

[0054] The training set S is known to consist of n sets of d-dimensional independent variables and n sets of c-dimensional dependent variables. The problem of learning the labeled distribution is transformed into a multiple regression analysis problem, that is, establishing the linear dependencies between multiple sets of independent and dependent variables. Then, the partial least squares (PLS) method is used to build a unified customer activity prediction model for all credit card products, i.e., a credit card inactive account prediction model. The independent variable matrix X and the dependent variable matrix Y are represented as follows:

[0055]

[0056] When establishing a multiple linear regression model, PLS needs to extract several pairs of latent components based on the correlation between the independent and dependent variables. In establishing a multiple regression model, PLS aims to maximize the covariance among these latent variables. Assuming there are n samples, taking the first pair of principal component axis vectors a1 and b1 of X and Y as an example, the optimization objective of PLS ​​can be formulated as:

[0057]

[0058] Where a1 and b1 are symmetric matrices X T YY T X and Y T XX T The unit eigenvectors corresponding to the largest eigenvalue of Y can be solved using Lagrange multipliers.

[0059] Based on the linear transformation, the first set of latent variables u1 and v1 for X and Y are extracted:

[0060] u1 = Xa1, v1 = Yb1 (6)

[0061] Based on u1 and v1, establish the regression equations for X and Y on the latent variables:

[0062]

[0063] Based on the correlation between u1 and v1, Y is transformed into a regression equation for the latent variable u1 of X:

[0064]

[0065] Among them, load vector E1, F1, and G1 are the residual matrices of the corresponding regression equations.

[0066] Treating E1 as X and F1 as Y, we extract the second pair of latent variables u2 and v2 to establish a new regression equation:

[0067]

[0068] Repeat the above steps until m pairs of latent variables are extracted:

[0069]

[0070] Formula (10) can be expressed in matrix form as follows:

[0071] Y=UR T +F = XAR T +F=Xβ+F (11)

[0072] Wherein, the regression coefficient β = AR T The residual matrix is ​​F.

[0073] After PLS establishes a regression model and obtains the regression coefficient β, it is used to analyze instance x. i Output a predicted label distribution The label corresponding to the minimum descriptive degree is x. i Least active customers

[0074]

[0075] It should be noted that the PLS regression model can consider the potential relationships between multiple dependent variables and overcome the multivariate correlation of variables. When the sample data is less than the number of variables, PLS can better guarantee the accuracy of the regression model.

[0076] Furthermore, an adaptive adjustment model is performed, that is, based on the initial regression model, the standard deviation is adaptively adjusted for each credit card product to obtain the regression model corresponding to each credit card product.

[0077] In one optional embodiment, based on the initial regression model, adaptive standard deviation adjustment is performed on each credit card product to obtain a regression model corresponding to each credit card product. This includes: configuring a first standard deviation for each credit card product, and determining an initial label distribution for each credit card product based on the first standard deviation and the label distribution corresponding to each credit card product; determining a predicted label distribution for each credit card product based on the initial regression model, and determining a target standard deviation for each credit card product based on the initial label distribution and the predicted label distribution corresponding to each credit card product; and updating the initial regression model based on the target standard deviation for each credit card product to obtain a regression model corresponding to each credit card product.

[0078] The PLS regression model is a unified inactive credit card customer prediction model based on all credit card products. Since different credit card products have different least active customers, an adaptive model adjustment is performed for each credit card product to identify the least active customers for each product, thereby achieving precise customer reactivation. The goal of the adaptive adjustment model is that the standard deviation σ of the discrete Gaussian distribution in formula (3) should be adapted to the least active customers of each credit card product, that is, a different standard deviation is assigned to each credit card product.

[0079] To achieve this goal, the labeled distributions of all credit card products are first initialized as discrete Gaussian distributions with initial standard deviations. Specifically, a first standard deviation (initial standard deviation) is assigned to each credit card product, and the initial labeled distribution for each product is determined based on this first standard deviation and the corresponding labeled distribution. Then, a partial least squares regression model is used to obtain the predicted labeled distributions for all credit card products; this is based on the initial regression model to determine the predicted labeled distribution for each product. Next, a "good" predicted labeled distribution is selected to adaptively learn the standard deviations of each credit card product. The labeled distributions of all credit card products are then updated based on these standard deviations to establish a new regression model. Finally, the coefficients and standard deviations of the regression model are iteratively updated until the algorithm converges (e.g., after a preset number of iterations). This means that a target standard deviation for each credit card product is determined based on its initial and predicted labeled distributions, and the initial regression model is updated based on this target standard deviation to obtain the regression model for each credit card product.

[0080] In one optional embodiment, the target standard deviation for each credit card product is determined based on the initial label distribution and the predicted label distribution for each credit card product. This includes: performing similarity calculations on the initial label distribution and the predicted label distribution for each credit card product to obtain the calculation results; and optimizing the first standard deviation with the goal of minimizing the calculation results to obtain the target standard deviation for each credit card product.

[0081] Optionally, similarity calculations are performed on the initial label distribution and the predicted label distribution corresponding to each credit card product to obtain the calculation results. Then, with the goal of minimizing the calculation results, the first standard deviation is optimized to obtain the target standard deviation corresponding to each credit card product.

[0082] Specifically, given a training set S, based on each least active customer α learned in the (k-1)th iteration... i Adaptive standard deviation Formula (3) is used for each credit card product x i Generate a label distribution The algorithm first initializes the standard deviation of all credit card products to a fixed constant, and then generates the initial label distribution of all credit card products using formula (3).

[0083] Then, the partial least squares method is used to establish the regression equation of the dependent variable matrix Y with respect to the independent variable matrix X, i.e., the PLS regression model. The solved regression coefficient β should make the predicted label distribution generated by the regression model similar to the label distribution generated by formula (3). Most similar. After training and generating the regression model Y = Xβ, for any credit card product x in the training set... i The corresponding predicted label distribution is obtained through this regression model. x i The model predicts customers as The absolute error of the model in predicting customers is The mean absolute error (MAE) over the entire training set.

[0084] Then update the standard deviation. Given the predicted label distributions for all credit card products, select the predicted label distributions with an absolute error lower than the MAE to learn the standard deviation for each inactive customer. The training set. The predicted label distribution samples in this training set show excellent learning ability in customer recommendation and are more suitable for training and learning to adapt to the standard deviation of each inactive customer. These "excellent" training samples can be divided into group c according to the least active customer corresponding to their credit card products. At the same time, the label distribution with the same standard deviation is generated for all credit card products in the same group by formula (3). Grouping all credit card products with the same least active customer in the same group is beneficial to the adaptive learning of the standard deviation of the product. The subscript set of all credit card products in the group with the least active customer α is denoted as

[0085] Formula (3) is the set I α All credit card products generate the same standard deviation σ. α The discrete label distribution, and I α Each credit card product x g ,g∈I α With a labeled distribution Related, that is:

[0086]

[0087] Where, g∈Iα ,j∈{1,2,…,c}.

[0088] Within the same group, the standard deviation σ α For credit card product α g The generated discrete Gaussian distribution It should be compared with the predicted label distribution calculated by the regression model. To achieve the greatest possible similarity, optionally, the KL divergence metric is used to measure the similarity between the labeled and predicted labeled distributions. In the k-th iteration, the optimal standard deviation σ of the credit card product α is... α The following optimizations are possible:

[0089]

[0090] Substituting formula (13) into formula (14) yields a nonlinear optimization problem, which is solved using the logarithmic barrier interior point method. This provides an adaptive inactive account prediction model for each credit card product.

[0091] It should be noted that by extracting multiple latent variables, the PLS method can handle multiple correlations between variables, ensuring the accuracy and stability of the model even when the sample size is less than the number of variables. By learning the relationship between independent and dependent variables, it provides a data-driven approach for predicting inactive customers, enabling the establishment of adaptive inactive customer prediction models for each credit card product. This allows for the screening of inactive customer groups for each credit card product, accurately identifying customers who may become inactive credit card customers in the future.

[0092] In one optional embodiment, after determining the target object of each credit card product from multiple predictable objects for each credit card product, a reminder message is sent to the target object of each credit card product, wherein the reminder message is used to remind the target object to use the card.

[0093] Optionally, after identifying the inactive customer groups for each credit card product, notification messages can be sent to these customers separately, and corresponding reactivation strategies can be adopted to improve their activity and achieve precise reactivation.

[0094] In this embodiment, a label distribution learning algorithm based on multiple multivariate regression is used for modeling. First, feature data of multiple predictable objects for at least one credit card product to be predicted are obtained. Then, the feature data of multiple predictable objects for each credit card product are input into the regression model corresponding to each credit card product for prediction, resulting in a predicted label distribution for each credit card product. This predicted label distribution represents the probability distribution of the predictable object's activity status with respect to the credit card product. Based on the predicted label distribution, the target object for each credit card product is determined from the multiple predictable objects. By establishing an adaptive inactive customer prediction model for each credit card product, inactive customer groups can be screened out for each product, accurately identifying customers who may become inactive credit card customers in the future. This achieves the goal of precisely reactivating inactive credit card customers, thereby improving accuracy and solving the technical problem of low accuracy in identifying inactive credit card customers in existing technologies.

[0095] Example 2

[0096] According to an embodiment of this application, an embodiment of a target object determination device is provided, wherein... Figure 3 This is a schematic diagram of an optional target object determination device according to an embodiment of this application, such as... Figure 3 As shown, the device includes: a first acquisition unit 301, a first processing unit 302, and a determination unit 303.

[0097] The first acquisition unit 301 is used to acquire feature data of multiple objects to be predicted for at least one credit card product to be predicted;

[0098] The first processing unit 302 is used to input the feature data of multiple objects to be predicted for each credit card product into the regression model corresponding to each credit card product for prediction, and obtain the prediction label distribution corresponding to each credit card product, wherein the prediction label distribution is a probability distribution representing the activity status of the objects to be predicted in relation to the credit card product.

[0099] The determination unit 303 is used to determine the target object of each credit card product from multiple objects to be predicted for each credit card product based on the prediction label distribution.

[0100] In this embodiment, the first acquisition unit 301 acquires feature data of multiple predictable objects for at least one credit card product to be predicted; the first processing unit 302 inputs the feature data of multiple predictable objects for each credit card product into the regression model corresponding to each credit card product for prediction, and obtains the prediction label distribution corresponding to each credit card product, wherein the prediction label distribution is a probability distribution representing the activity status of the predictable object with respect to the credit card product; the determination unit 303 determines the target object of each credit card product from the multiple predictable objects for each credit card product based on the prediction label distribution. By establishing an adaptive inactive customer prediction model for each credit card product, inactive customer groups can be screened out for each credit card product, accurately locating customers who may become inactive credit card customers in the future, achieving the purpose of precise reactivation of inactive credit card customers, thereby improving the technical effect of improving accuracy, and thus solving the technical problem of low accuracy in identifying inactive customers of credit card products in the prior art.

[0101] It should be noted that the first acquisition unit 301, the first processing unit 302, and the determination unit 303 mentioned above correspond to steps S101 to S103 in the above embodiments. The three units and the corresponding steps implement the same examples and application scenarios, but are not limited to the content disclosed in the above embodiment 1.

[0102] Furthermore, the determining unit includes: a comparison subunit, used to compare the probability value corresponding to each object to be predicted in the prediction label distribution with a preset threshold; and a determining subunit, used to select the object to be predicted among multiple objects to be predicted whose probability value is greater than the preset threshold as the target object.

[0103] Furthermore, the device also includes the following units for obtaining a regression model corresponding to each credit card product through the following steps: a second acquisition unit for acquiring historical card usage data corresponding to each credit card product and vectorizing the historical card usage data to obtain a card usage feature vector corresponding to each credit card product; a second processing unit for constructing a discrete Gaussian distribution based on the card usage feature vector corresponding to each credit card product to obtain a labeled distribution corresponding to each credit card product; a third processing unit for constructing an independent variable matrix and a dependent variable matrix based on the labeled distribution corresponding to each credit card product, and establishing an initial regression model using partial least squares method based on the independent variable matrix and the dependent variable matrix, wherein the independent variable matrix is ​​used to represent the feature information of all credit card products, and the dependent variable matrix is ​​used to represent the activity information of the sample object for each credit card product; and a fourth processing unit for adaptively adjusting the standard deviation of each credit card product based on the initial regression model to obtain a regression model corresponding to each credit card product.

[0104] Furthermore, the third processing unit includes: a first processing subunit for constructing the linear dependency relationship between the independent variable matrix and the dependent variable matrix; and a second processing subunit for extracting multiple pairs of latent variables related to the independent and dependent variables based on the linear dependency relationship, and maximizing the covariance between the latent variables to obtain the initial regression model.

[0105] Furthermore, the fourth processing unit includes: a third processing subunit, used to configure a first standard deviation for each credit card product, and determine the initial label distribution corresponding to each credit card product based on the first standard deviation and the label distribution corresponding to each credit card product; a fourth processing subunit, used to determine the predicted label distribution corresponding to each credit card product based on the initial regression model, and determine the target standard deviation corresponding to each credit card product based on the initial label distribution and the predicted label distribution corresponding to each credit card product; and a fifth processing subunit, used to update the initial regression model based on the target standard deviation corresponding to each credit card product to obtain the regression model corresponding to each credit card product.

[0106] Furthermore, the fourth processing subunit includes: a calculation module, used to perform similarity calculation on the initial label distribution and the predicted label distribution corresponding to each credit card product to obtain the calculation result; and a processing module, used to optimize the first standard deviation with the goal of minimizing the calculation result to obtain the target standard deviation corresponding to each credit card product.

[0107] Furthermore, the device also includes a sending unit, configured to send a prompt message to each target object of a credit card product after determining the target object of each credit card product from multiple predictable objects of each credit card product, wherein the prompt message is used to remind the target object of card usage.

[0108] Example 3

[0109] Embodiments of this application may provide an electronic device. Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 Only one of the following is shown: processor 402, memory 404, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0110] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0111] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: acquiring feature data of multiple objects to be predicted for at least one credit card product; inputting the feature data of multiple objects to be predicted for each credit card product into the regression model corresponding to each credit card product for prediction, obtaining the prediction label distribution corresponding to each credit card product, wherein the prediction label distribution is a probability distribution representing the activity status of the objects to be predicted in relation to the credit card product; and determining the target object of each credit card product from the multiple objects to be predicted for each credit card product based on the prediction label distribution.

[0112] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: compare the probability value corresponding to each object to be predicted in the prediction label distribution with a preset threshold; and select the object to be predicted whose probability value is greater than the preset threshold from among the multiple objects to be predicted as the target object.

[0113] The processor can also access information and applications stored in the memory via a transmission device to execute the following steps: acquire historical card usage data for each credit card product, and vectorize the historical card usage data to obtain a card usage feature vector for each credit card product; construct a discrete Gaussian distribution based on the card usage feature vector for each credit card product to obtain a labeled distribution for each credit card product; construct independent variable matrices and dependent variable matrices based on the labeled distribution for each credit card product, and establish an initial regression model using partial least squares based on the independent variable matrices and dependent variable matrices, where the independent variable matrix represents the feature information of all credit card products, and the dependent variable matrix represents the activity information of the sample objects for each credit card product; and perform adaptive standard deviation adjustment for each credit card product based on the initial regression model to obtain a regression model for each credit card product.

[0114] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: constructing the linear dependency between the independent variable matrix and the dependent variable matrix; based on the linear dependency, extracting multiple pairs of latent variables related to the independent and dependent variables, and maximizing the covariance between the latent variables to obtain the initial regression model.

[0115] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: configure a first standard deviation for each credit card product, and determine the initial label distribution for each credit card product based on the first standard deviation and the label distribution corresponding to each credit card product; determine the predicted label distribution for each credit card product based on the initial regression model, and determine the target standard deviation for each credit card product based on the initial label distribution and the predicted label distribution corresponding to each credit card product; update the initial regression model based on the target standard deviation for each credit card product to obtain the regression model for each credit card product.

[0116] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: perform similarity calculation on the initial label distribution and the predicted label distribution corresponding to each credit card product to obtain the calculation result; optimize the first standard deviation with the goal of minimizing the calculation result to obtain the target standard deviation corresponding to each credit card product.

[0117] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: after determining the target object of each credit card product from multiple predictable objects for each credit card product, sending a prompt message to the target object of each credit card product respectively, wherein the prompt message is used to remind the target object to use the card.

[0118] Those skilled in the art will understand that Figure 4 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones (such as Android phones, iOS phones, etc.), tablets, PDAs, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 4 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 4 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 4 The different configurations shown.

[0119] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0120] Example 4

[0121] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for determining the target object provided in Embodiment 1.

[0122] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0123] This application also provides a computer program product that, when executed on a data processing device, is suitable for performing method steps for determining a target object.

[0124] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0125] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0126] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0127] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0128] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0129] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0130] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for determining a target object, characterized in that, include: Obtain feature data of multiple objects to be predicted for at least one credit card product; The feature data of multiple objects to be predicted for each credit card product are input into the regression model corresponding to each credit card product for prediction, and the prediction label distribution corresponding to each credit card product is obtained. The prediction label distribution is a probability distribution representing the activity status of the objects to be predicted in relation to the credit card product. Based on the predicted label distribution, the target object of each credit card product is determined from multiple objects to be predicted for each credit card product; Specifically, determining the target object for each credit card product from multiple objects to be predicted based on the predicted label distribution includes: The probability value corresponding to each object to be predicted in the predicted label distribution is compared with a preset threshold. Among the plurality of objects to be predicted, the object whose probability value is greater than the preset threshold is taken as the target object; The regression model for each credit card product is obtained through the following steps: Obtain historical card usage data corresponding to each credit card product, and vectorize the historical card usage data to obtain the card usage feature vector corresponding to each credit card product; A discrete Gaussian distribution is constructed based on the card usage feature vector corresponding to each credit card product to obtain the label distribution corresponding to each credit card product; Based on the label distribution corresponding to each credit card product, an independent variable matrix and a dependent variable matrix are constructed. Based on the independent variable matrix and the dependent variable matrix, an initial regression model is established using partial least squares method. The independent variable matrix is ​​used to represent the feature information of all credit card products, and the dependent variable matrix is ​​used to represent the activity information of the sample objects for each credit card product. Based on the initial regression model, adaptive standard deviation adjustment is performed on each credit card product to obtain the regression model corresponding to each credit card product; Specifically, based on the initial regression model, adaptive standard deviation adjustment is performed on each credit card product to obtain the regression model corresponding to each credit card product, including: A first standard deviation is configured for each credit card product, and an initial label distribution corresponding to each credit card product is determined based on the first standard deviation and the label distribution corresponding to each credit card product; Based on the initial regression model, the predicted label distribution corresponding to each credit card product is determined, and based on the initial label distribution and the predicted label distribution corresponding to each credit card product, the target standard deviation corresponding to each credit card product is determined. The initial regression model is updated based on the target standard deviation corresponding to each credit card product to obtain the regression model corresponding to each credit card product.

2. The method according to claim 1, characterized in that, Based on the independent variable matrix and the dependent variable matrix, an initial regression model is established using partial least squares, including: Construct the linear dependency relationship between the independent variable matrix and the dependent variable matrix; Based on the linear dependency, multiple pairs of latent variables related to the independent and dependent variables are extracted, and the covariance among the latent variables is maximized to obtain the initial regression model.

3. The method according to claim 1, characterized in that, Based on the initial label distribution and the predicted label distribution corresponding to each credit card product, the target standard deviation corresponding to each credit card product is determined, including: A similarity calculation is performed on the initial label distribution and the predicted label distribution corresponding to each credit card product to obtain the calculation result; With the goal of minimizing the calculation result, the first standard deviation is optimized to obtain the target standard deviation for each credit card product.

4. The method according to claim 1, characterized in that, After determining the target object for each credit card product from a plurality of objects to be predicted for each credit card product, the method further includes: A reminder message is sent to the target object of each credit card product, wherein the reminder message is used to remind the target object of card usage.

5. A device for determining a target object, characterized in that, include: The first acquisition unit is used to acquire feature data of multiple objects to be predicted for at least one credit card product to be predicted; The first processing unit is used to input the feature data of multiple objects to be predicted for each credit card product into the regression model corresponding to each credit card product for prediction, and obtain the prediction label distribution corresponding to each credit card product, wherein the prediction label distribution is a probability distribution representing the activity status of the objects to be predicted in relation to the credit card product; A determining unit is configured to determine the target object of each credit card product from a plurality of objects to be predicted for each credit card product based on the predicted label distribution; The determining unit includes: a comparison subunit, used to compare the probability value corresponding to each object to be predicted in the prediction label distribution with a preset threshold; and a determining subunit, used to select the object to be predicted among multiple objects to be predicted whose probability value is greater than the preset threshold as the target object. The system also includes the following units for obtaining the regression model for each credit card product through the following steps: a second acquisition unit for acquiring historical card usage data for each credit card product and vectorizing the historical card usage data to obtain the card usage feature vector for each credit card product; a second processing unit for constructing a discrete Gaussian distribution based on the card usage feature vector for each credit card product to obtain the labeled distribution for each credit card product; a third processing unit for constructing an independent variable matrix and a dependent variable matrix based on the labeled distribution for each credit card product, and establishing an initial regression model using partial least squares based on the independent variable matrix and the dependent variable matrix, wherein the independent variable matrix is ​​used to represent the feature information of all credit card products, and the dependent variable matrix is ​​used to represent the activity information of the sample objects for each credit card product; and a fourth processing unit for adaptively adjusting the standard deviation for each credit card product based on the initial regression model to obtain the regression model for each credit card product. The fourth processing unit includes: a third processing subunit, used to configure a first standard deviation for each credit card product, and determine the initial label distribution for each credit card product based on the first standard deviation and the label distribution corresponding to each credit card product; a fourth processing subunit, used to determine the predicted label distribution for each credit card product based on the initial regression model, and determine the target standard deviation for each credit card product based on the initial label distribution and the predicted label distribution corresponding to each credit card product; and a fifth processing subunit, used to update the initial regression model based on the target standard deviation for each credit card product to obtain the regression model for each credit card product.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the method for determining the target object as described in any one of claims 1 to 4 when it is run.

7. An electronic device, characterized in that, The electronic device includes one or more processors; A memory for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to be configured to run the programs, wherein the programs are configured to execute the method for determining the target object as described in any one of claims 1 to 4.

Images