Product recommendation method and device, storage medium and electronic equipment

Abstract

The invention discloses a product recommendation method and device, a storage medium and electronic equipment. Relates to the technical field of artificial intelligence, and comprises the following steps: obtaining initial data information of a target object, the initial data information at least comprising historical transaction data of the target object; obtaining a target feature set of the target object according to the initial data information; processing the target feature set through a target random forest model to obtain preference probability values of the target object for a plurality of financial products; and determining a target financial product to be recommended according to the preference probability values of the plurality of financial products, and recommending the target financial product to the target object. Through the method and the device, the problem of relatively low product recommendation accuracy caused by recommending corresponding financial products to the user based on the purchase rate of the financial products in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and more specifically, to a product recommendation method and device, a storage medium, and an electronic device. Background Art

[0002] As competition in the financial sector intensifies, traditional financial institutions are faced with the problem of difficulty in meeting the diverse needs of customers. In order to improve the user experience of purchasing financial products and provide users with better services, the purchase rate of each financial product is counted, and then financial products are recommended to users based on the purchase rate of financial products. However, this method does not take into account the actual needs of users, and therefore, there is a problem of low accuracy in product recommendations.

[0003] Currently, no effective solution has been proposed to address the problem that in related technologies, corresponding financial products are recommended to users based on the purchase rate of financial products, resulting in relatively low accuracy of product recommendations. Summary of the invention

[0004] The main purpose of the present application is to provide a product recommendation method and device, a storage medium and an electronic device to solve the problem in the related art that corresponding financial products are recommended to users based on the purchase rate of financial products, resulting in relatively low accuracy of product recommendations.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a product recommendation method is provided. The method comprises: obtaining initial data information of a target object, wherein the initial data information at least includes historical transaction data of the target object; obtaining a target feature set of the target object based on the initial data information; processing the target feature set through a target random forest model to obtain a preference probability value of the target object for multiple financial products; determining a target financial product to be recommended based on the preference probability values ​​of the multiple financial products, and recommending the target financial product to the target object.

[0006] Furthermore, the target feature set is processed by a target random forest model to obtain the preference probability value of the target object for multiple financial products, including: voting for the multiple financial products based on the target feature set by multiple decision trees in the target random forest model to obtain the number of votes corresponding to each financial product; and calculating according to the number of votes corresponding to each financial product to obtain the preference probability value of the target object for each financial product.

[0007] Furthermore, calculating according to the number of votes corresponding to each financial product to obtain the target object's preference probability value for each financial product includes: calculating according to the number of votes corresponding to each financial product and the number of the multiple decision trees to obtain a proportion value corresponding to each financial product; obtaining the historical purchase rate of each financial product; and calculating according to the proportion value corresponding to each financial product and the historical purchase rate of each financial product to obtain the preference probability value.

[0008] Furthermore, determining the target financial product to be recommended based on the preference probability values ​​of the multiple financial products includes: obtaining attribute information of the target object, wherein the attribute information includes at least: age information and gender information of the target object; constructing a target profile of the target object based on the attribute information and the preference probability value; and determining the target financial product to be recommended based on the target profile of the target object.

[0009] Furthermore, based on the initial data information, obtaining the target feature set of the target object includes: preprocessing the initial data information to obtain the target data information; calculating based on the transaction frequency and transaction amount in the target data information to obtain a first feature value; calculating based on the historical financial product information in the target data information to obtain a second feature value; calculating the stability of the target object based on the historical transaction data in the target data information to obtain a third feature value; calculating based on the credit limit information in the target data information to obtain a fourth feature value; obtaining the target feature set based on the first feature value, the second feature value, the third feature value and the fourth feature value.

[0010] Furthermore, the target random forest model is obtained by adopting the following steps: obtaining a target training set based on a historical feature set of multiple historical objects and a true label corresponding to each historical object; randomly sampling the target training set to obtain multiple training subsets; creating multiple decision trees based on the multiple training subsets, and training the multiple decision trees based on the multiple training subsets to obtain the target random forest model.

[0011] Furthermore, after recommending the target financial product to the target object, the method also includes: obtaining transaction data information of the target object in a preset time period; obtaining transaction volume information of the multiple financial products in the preset time period; based on the transaction data information and the transaction volume information, determining the financial product to be recommended again, and recommending the financial product to be recommended to the target object.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a product recommendation device is provided. The device comprises: a first acquisition unit, used to acquire initial data information of a target object, wherein the initial data information at least includes historical transaction data of the target object; a first processing unit, used to obtain a target feature set of the target object based on the initial data information; a second processing unit, used to process the target feature set through a target random forest model to obtain a preference probability value of the target object for multiple financial products; a first determination unit, used to determine a target financial product to be recommended based on the preference probability values ​​of the multiple financial products, and recommend the target financial product to the target object.

[0013] Furthermore, the second processing unit includes: a voting module, used to vote for the multiple financial products based on the target feature set through multiple decision trees in the target random forest model to obtain the number of votes corresponding to each financial product; a first calculation module, used to calculate according to the number of votes corresponding to each financial product to obtain the preference probability value of the target object for each financial product.

[0014] Furthermore, the first calculation module includes: a first calculation submodule, used to calculate based on the number of votes corresponding to each financial product and the number of the multiple decision trees to obtain a proportion value corresponding to each financial product; an acquisition submodule, used to obtain the historical purchase rate of each financial product; and a second calculation submodule, used to calculate based on the proportion value corresponding to each financial product and the historical purchase rate of each financial product to obtain the preference probability value.

[0015] Furthermore, the first determination unit includes: an acquisition submodule, used to acquire attribute information of the target object, wherein the attribute information at least includes: age information and gender information of the target object; a construction submodule, used to construct a target portrait of the target object based on the attribute information and the preference probability value; and a determination submodule, used to determine the target financial product to be recommended based on the target portrait of the target object.

[0016] Furthermore, the first processing unit includes: a processing module, which is used to pre-process the initial data information to obtain target data information; a second calculation module, which is used to calculate based on the transaction frequency and transaction amount in the target data information to obtain a first eigenvalue; a third calculation module, which is used to calculate based on the historical financial product information in the target data information to obtain a second eigenvalue; a fourth calculation module, which is used to calculate the stability of the target object based on the historical transaction data in the target data information to obtain a third eigenvalue; a fifth calculation module, which is used to calculate based on the credit limit information in the target data information to obtain a fourth eigenvalue; a determination module, which is used to obtain the target feature set based on the first eigenvalue, the second eigenvalue, the third eigenvalue and the fourth eigenvalue.

[0017] Furthermore, the target random forest model is obtained by using the following devices: a second determination unit, used to obtain a target training set based on a historical feature set of multiple historical objects and a true label corresponding to each historical object; a sampling unit, used to randomly sample the target training set to obtain multiple training subsets; a training unit, used to create multiple decision trees based on the multiple training subsets, and train the multiple decision trees based on the multiple training subsets to obtain the target random forest model.

[0018] Furthermore, the device also includes: a second acquisition unit, used to acquire transaction data information of the target object in a preset time period after recommending the target financial product to the target object; a third acquisition unit, used to acquire transaction volume information of the multiple financial products in the preset time period; and a third determination unit, used to re-determine the financial product to be recommended based on the transaction data information and the transaction volume information, and recommend the financial product to be recommended to the target object.

[0019] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the product recommendation methods described above.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes any one of the product recommendation methods described above when running.

[0021] In an embodiment of the present application, initial data information of a target object is obtained, wherein the initial data information includes at least historical transaction data of the target object; a target feature set of the target object is obtained based on the initial data information; the target feature set is processed by a target random forest model to obtain a preference probability value of the target object for a plurality of financial products; a target financial product to be recommended is determined based on the preference probability values ​​of the plurality of financial products, and the target financial product is recommended to the target object, thereby solving a technical problem in the related art of recommending corresponding financial products to users based on the purchase rate of the financial products, resulting in relatively low accuracy of product recommendations.

[0022] In this solution, the historical transaction data of the target object is obtained, and the target feature set used to characterize the target object is determined based on the historical transaction data. The target feature set is then processed through a target random forest model to obtain the target object's preference probability values ​​for multiple financial products. Finally, the target financial products to be recommended are determined based on the preference probability values ​​of multiple financial products. The target feature set can be used to accurately evaluate the target object's behavior and preferences, and the target financial products to be recommended can be determined more accurately, thereby achieving the effect of improving the accuracy of product recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 A hardware structure block diagram of a computer terminal for implementing a product recommendation method is shown;

[0025] Figure 2 is a flowchart of a product recommendation method provided according to an embodiment of the present application;

[0026] Figure 3 is a schematic diagram of a product recommendation device provided according to an embodiment of the present application;

[0027] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work 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 and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0031] Example 1

[0032] According to an embodiment of the present application, a method embodiment of a product recommendation is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing a product recommendation method. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0034] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0035] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the product recommendation method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned product recommendation method. The memory 104 may include a high-speed random access memory, and may also include a 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 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0036] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0037] The display may be a touch screen type liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0038] Under the above operating environment, this application provides Figure 2 Product recommendation method shown. Figure 2 It is a flowchart of the product recommendation method according to the first embodiment of the present application.

[0039] Step S201, obtaining initial data information of a target object, wherein the initial data information at least includes historical transaction data of the target object.

[0040] Optionally, initial data information of the user (i.e., the target object mentioned above) can be obtained from the information management system of the financial institution, for example, historical transaction data of the target object in the initial data information, including transaction products, transaction frequency, transaction amount, loan interest rate, credit score and other data.

[0041] Step S202: obtaining a target feature set of the target object according to the initial data information.

[0042] Optionally, the initial data information is processed to obtain a target feature set of the user. For example, the initial data information may be encoded by an encoder, and then the encoded information is used as a target feature set of the target object.

[0043] Step S203, processing the target feature set through the target random forest model to obtain the target object's preference probability values ​​for multiple financial products.

[0044] Optionally, the target feature set is processed using the target random forest model to obtain the target object's preference probability values ​​for multiple financial products. For example, the target random forest model is used to vote on whether the user likes a certain financial product based on the target feature set, and then the preference probability values ​​of the above multiple financial products are obtained according to the voting results.

[0045] Step S204, determining a target financial product to be recommended based on the preference probability values ​​of the plurality of financial products, and recommending the target financial product to the target object.

[0046] Optionally, after obtaining the preference probability values ​​of the plurality of financial products, a target financial product to be recommended is determined from the plurality of financial products according to the preference probability values, and the target financial product is recommended to the target object.

[0047] To summarize, the historical transaction data of the target object is obtained, and the target feature set used to characterize the target object is determined based on the historical transaction data. The target feature set is then processed through the target random forest model to obtain the target object's preference probability values ​​for multiple financial products. Finally, the target financial products to be recommended are determined based on the preference probability values ​​of multiple financial products. The target feature set can be used to accurately evaluate the target object's behavior and preferences, and the target financial products to be recommended can be determined more accurately, thereby achieving the effect of improving the accuracy of product recommendations.

[0048] Optionally, in the product recommendation method provided in the embodiment of the present application, the target feature set is processed by a target random forest model to obtain the target object's preference probability value for multiple financial products, including: voting for multiple financial products based on the target feature set through multiple decision trees in the target random forest model to obtain the number of votes corresponding to each financial product; and calculating according to the number of votes corresponding to each financial product to obtain the target object's preference probability value for each financial product.

[0049] In an optional embodiment, the target object's preference probability values ​​for multiple financial products can be obtained by the following steps: multiple decision trees in the target random forest model, the main goal is to predict the customer's behavior or attributes, such as determining whether the customer is interested in a certain product, which usually belongs to a classification task, wherein the goal of the model is to map the input data to discrete categories or labels. For example, multiple decision trees in the target random forest model vote for multiple financial products based on the target feature set to obtain the number of votes corresponding to each financial product, and finally calculate according to the number of votes corresponding to each financial product to obtain the target object's preference probability value for each financial product. For example, the preference probability of a financial product is obtained according to the ratio between the number of votes corresponding to each financial product and the number of multiple decision trees.

[0050] The random forest model can more accurately understand the characteristics and behavior patterns of customers, thereby improving the accuracy of the preference probability values.

[0051] Optionally, in the product recommendation method provided in the embodiment of the present application, calculation is performed based on the number of votes corresponding to each financial product to obtain the target object's preference probability value for each financial product, including: calculation is performed based on the number of votes corresponding to each financial product and the number of multiple decision trees to obtain a proportion value corresponding to each financial product; obtaining the historical purchase rate of each financial product; and calculation is performed based on the proportion value corresponding to each financial product and the historical purchase rate of each financial product to obtain a preference probability value.

[0052] In an optional embodiment, when calculating the preference probability value of each financial product, the following includes: first, calculating the ratio between the number of votes corresponding to each financial product and the number of multiple decision trees to obtain the corresponding proportion value of each financial product. Then, the number of purchases of each financial product in the historical time period is counted, and then the historical purchase rate of each financial product is calculated based on the purchase number. Finally, the preference probability value is calculated based on the proportion value corresponding to each financial product and the historical purchase rate of each financial product. For example, the proportion value corresponding to each financial product and the historical purchase rate of each financial product can be processed by a deep learning model, and then the corresponding preference probability value is output by the deep learning model.

[0053] The ratio between the number of votes and the number of decision trees as well as the historical purchase rate of financial products can be used to more accurately assess the user's preference for financial products, thereby improving the accuracy of subsequent recommendations for financial products.

[0054] Optionally, in the product recommendation method provided in the embodiment of the present application, determining the target financial product to be recommended based on the preference probability values ​​of multiple financial products includes: obtaining attribute information of the target object, wherein the attribute information includes at least: age information and gender information of the target object; constructing a target portrait of the target object based on the attribute information and the preference probability value; and determining the target financial product to be recommended based on the target portrait of the target object.

[0055] In an optional embodiment, the following steps may be used to determine the target financial product to be recommended: obtaining the user's attribute information, which may include the user's age information and gender information; constructing the user's target profile based on the user's age information and gender information and the preference probability value; and finally determining the target financial product to be recommended based on the user's target profile.

[0056] By building user portraits, we can better understand user needs and improve the accuracy of product recommendations.

[0057] Optionally, in the product recommendation method provided in the embodiment of the present application, obtaining a target feature set of the target object based on the initial data information includes: preprocessing the initial data information to obtain the target data information; calculating based on the transaction frequency and transaction amount in the target data information to obtain a first eigenvalue; calculating based on the historical financial product information in the target data information to obtain a second eigenvalue; calculating the stability of the target object based on the historical transaction data in the target data information to obtain a third eigenvalue; calculating based on the credit limit information in the target data information to obtain a fourth eigenvalue; obtaining the target feature set based on the first eigenvalue, the second eigenvalue, the third eigenvalue and the fourth eigenvalue.

[0058] In an optional embodiment, the target feature set is obtained by adopting the following steps: First, the initial data information is preprocessed to obtain the target data information, for example, the main steps of data preprocessing are:

[0059] (1) Missing value processing: Missing values ​​refer to the empty or missing values ​​of certain fields in the data set, which is a common problem in data preprocessing. Methods for processing missing values ​​include deletion, filling, and interpolation. For rows or columns with fewer missing values, they can be deleted directly. The filling method can use fixed values, mean, median, mode, etc. to fill missing values. Here, the mean can be used for filling.

[0060] (2) Deduplication: Deduplication is the process of eliminating duplicate samples in the data. For duplicate data in credit assessment, the duplicate rows in the data set can be directly deleted.

[0061] (3) Outlier processing: Outliers refer to values ​​in the data set that are significantly different from normal values ​​and may have a negative impact on the model. The processing methods can be deletion and filling methods. Data that is significantly deviated from the normal range can be deleted.

[0062] Through the above data preprocessing steps, missing values, duplicate data and outliers can be effectively processed, thereby improving the accuracy of target data information.

[0063] Then the feature combination can help to explore the complexity of customer behavior. Therefore, the first feature value can be calculated through the transaction frequency and transaction amount in the target data information. The first feature value can more comprehensively reflect the overall activity and transaction value of the user.

[0064] The second eigenvalue is calculated by the historical financial product information in the target data information, and the second eigenvalue helps to better understand the user's product preferences; the third eigenvalue is calculated by the stability of the target object through the historical transaction data in the target data information, for example, the third eigenvalue is obtained based on the standard deviation of the average monthly transaction amount and the mean of the average monthly transaction amount in the historical transaction data. By calculating the ratio of the standard deviation to the mean, the stability of the customer's transaction behavior is quantified, which has a reference value for predicting future behavior. For example, the third eigenvalue is (1-standard deviation of the average monthly transaction amount / mean of the average monthly transaction amount) × 100. The fourth eigenvalue can also be calculated by the credit limit information in the target data information, which helps to understand the customer's credit card usage status and has an important reference value for credit scoring and risk management.

[0065] In an optional embodiment, the customer activity index of multiple products can also be used to obtain the fifth eigenvalue, which is: (credit card transaction number + savings account transaction number) × the average number of product types used per month; the sixth eigenvalue can also be obtained by squaring the average transaction amount, and the impact of the transaction amount on customer value can be better captured by introducing a nonlinear relationship between the amount; the loan interest rate and the customer credit score can also be combined as the seventh eigenvalue, etc.; the credit limit usage feature can also be combined. Finally, based on the above eigenvalues, the target feature set is obtained.

[0066] Feature combination helps to more comprehensively describe customer behavior and characteristics, and selects appropriate combination methods based on actual conditions and problem requirements, thereby improving the modeling effect of bank customer portraits.

[0067] Optionally, in the product recommendation method provided in the embodiment of the present application, the following steps are adopted to obtain the target random forest model: based on the historical feature sets of multiple historical objects and the true label corresponding to each historical object, a target training set is obtained; the target training set is randomly sampled to obtain multiple training subsets; based on the multiple training subsets, multiple decision trees are created, and the multiple decision trees are trained based on the multiple training subsets to obtain the target random forest model.

[0068] In an optional embodiment, the target random forest model is obtained by the following steps: a target training set is obtained through a historical feature set of multiple historical objects and the true label corresponding to each historical object, the target training set is randomly sampled to generate multiple training subsets, and an independent decision tree is constructed for each training subset using a decision tree algorithm. When making decisions at each node, a feature is randomly selected for division to reduce the correlation between the decision trees and increase the diversity of the overall model. For classification tasks, the results of each decision tree are summarized through a voting mechanism, and the category with the most votes is selected as the final prediction result. For regression tasks, the average of the results of each tree is taken.

[0069] The random forest model reduces the risk of overfitting by introducing randomness, and is able to handle large-scale, high-dimensional data. Its voting mechanism and average operation make the model more robust and can make more accurate predictions for different customer profiles, thus providing a reliable foundation for the generation of personalized marketing strategies.

[0070] Optionally, in the product recommendation method provided in the embodiment of the present application, after recommending the target financial product to the target object, the method also includes: obtaining transaction data information of the target object in a preset time period; obtaining transaction volume information of multiple financial products in a preset time period; based on the transaction data information and the transaction volume information, re-determining the financial product to be recommended, and recommending the financial product to be recommended to the target object.

[0071] In an optional embodiment, after the target financial product is recommended to the target object, the transaction data information of the target object in a preset time period and the transaction volume information of each financial product in the preset time period can be obtained again. Finally, the financial product to be recommended is adjusted according to the transaction data information and the transaction volume information, and the financial product to be recommended is determined again to be recommended to the target object.

[0072] In an optional embodiment, the recommendation effect of financial products can also be evaluated: collect and monitor various data related to recommendation activities, including but not limited to customer transaction records, feedback information, and market response. Set several performance indicators to evaluate the effectiveness of marketing strategies. These indicators may include: customer engagement, transaction growth rate, customer satisfaction, etc.

[0073] Customer Engagement:

[0074]

[0075] Transaction Growth Rate (TGR):

[0076]

[0077] Customer Satisfaction: You can use an appropriate survey or feedback score, such as a rating from 1 to 5, and then calculate the average score.

[0078] Through the above steps, financial institutions can timely understand the actual effect of the recommended strategy, adjust the strategy according to data feedback, achieve dynamic optimization, and improve the effect of marketing and customer satisfaction. This process can ensure the real-time adaptability and flexibility of the strategy.

[0079] The product recommendation method provided in the embodiment of the present application obtains initial data information of the target object, wherein the initial data information includes at least the historical transaction data of the target object; obtains a target feature set of the target object based on the initial data information; processes the target feature set through a target random forest model to obtain the target object's preference probability value for multiple financial products; determines the target financial product to be recommended based on the preference probability values ​​of the multiple financial products, and recommends the target financial product to the target object, thereby solving the technical problem in the related art that the corresponding financial product is recommended to the user based on the purchase rate of the financial product, resulting in relatively low accuracy of the product recommendation.

[0080] In this solution, the historical transaction data of the target object is obtained, and the target feature set used to characterize the target object is determined based on the historical transaction data. The target feature set is then processed through a target random forest model to obtain the target object's preference probability values ​​for multiple financial products. Finally, the target financial products to be recommended are determined based on the preference probability values ​​of multiple financial products. The target feature set can be used to accurately evaluate the target object's behavior and preferences, and the target financial products to be recommended can be determined more accurately, thereby achieving the effect of improving the accuracy of product recommendations.

[0081] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0082] Example 2

[0083] The embodiment of the present application also provides a product recommendation device. It should be noted that the product recommendation device of the embodiment of the present application can be used to execute the product recommendation method provided by the embodiment of the present application. The product recommendation device provided by the embodiment of the present application is introduced below.

[0084] According to an embodiment of the present application, a device for implementing the above product recommendation method is also provided, such as Figure 3 As shown, the device includes: a first acquisition unit 301, a first processing unit 302, a second processing unit 303 and a first determination unit 304.

[0085] A first acquisition unit 301 is used to acquire initial data information of a target object, wherein the initial data information at least includes historical transaction data of the target object;

[0086] The first processing unit 302 is used to obtain a target feature set of a target object according to the initial data information;

[0087] The second processing unit 303 is used to process the target feature set through the target random forest model to obtain the preference probability values ​​of the target object for multiple financial products;

[0088] The first determining unit 304 is configured to determine a target financial product to be recommended according to the preference probability values ​​of the plurality of financial products, and recommend the target financial product to the target object.

[0089] The product recommendation device provided in the embodiment of the present application obtains initial data information of the target object through the first acquisition unit 301, wherein the initial data information at least includes historical transaction data of the target object; the first processing unit 302 obtains a target feature set of the target object based on the initial data information; the second processing unit 303 processes the target feature set through a target random forest model to obtain the preference probability value of the target object for multiple financial products; the first determination unit 304 determines the target financial product to be recommended based on the preference probability values ​​of the multiple financial products, and recommends the target financial product to the target object, thereby solving the technical problem in the related art that the corresponding financial product is recommended to the user based on the purchase rate of the financial product, resulting in relatively low accuracy of product recommendation.

[0090] In this solution, the historical transaction data of the target object is obtained, and the target feature set used to characterize the target object is determined based on the historical transaction data. The target feature set is then processed through a target random forest model to obtain the target object's preference probability values ​​for multiple financial products. Finally, the target financial products to be recommended are determined based on the preference probability values ​​of multiple financial products. The target feature set can be used to accurately evaluate the target object's behavior and preferences, and the target financial products to be recommended can be determined more accurately, thereby achieving the effect of improving the accuracy of product recommendations.

[0091] Optionally, in the product recommendation device provided in the embodiment of the present application, the second processing unit includes: a voting module, used to vote for multiple financial products based on a target feature set through multiple decision trees in a target random forest model to obtain the number of votes corresponding to each financial product; a first calculation module, used to calculate based on the number of votes corresponding to each financial product to obtain the target object's preference probability value for each financial product.

[0092] Optionally, in the product recommendation device provided in the embodiment of the present application, the first calculation module includes: a first calculation sub-module, used to calculate based on the number of votes corresponding to each financial product and the number of multiple decision trees to obtain a proportion value corresponding to each financial product; an acquisition sub-module, used to obtain the historical purchase rate of each financial product; a second calculation sub-module, used to calculate based on the proportion value corresponding to each financial product and the historical purchase rate of each financial product to obtain a preference probability value.

[0093] Optionally, in the product recommendation device provided in the embodiment of the present application, the first determination unit includes: an acquisition submodule, used to acquire attribute information of the target object, wherein the attribute information includes at least: age information and gender information of the target object; a construction submodule, used to construct a target portrait of the target object based on the attribute information and the preference probability value; and a determination submodule, used to determine the target financial product to be recommended based on the target portrait of the target object.

[0094] Optionally, in the product recommendation device provided in the embodiment of the present application, the first processing unit includes: a processing module, which is used to pre-process the initial data information to obtain target data information; a second calculation module, which is used to calculate based on the transaction frequency and transaction amount in the target data information to obtain a first eigenvalue; a third calculation module, which is used to calculate based on the historical financial product information in the target data information to obtain a second eigenvalue; a fourth calculation module, which is used to calculate the stability of the target object based on the historical transaction data in the target data information to obtain a third eigenvalue; a fifth calculation module, which is used to calculate based on the credit limit information in the target data information to obtain a fourth eigenvalue; a determination module, which is used to obtain a target feature set based on the first eigenvalue, the second eigenvalue, the third eigenvalue and the fourth eigenvalue.

[0095] Optionally, in the product recommendation device provided in the embodiment of the present application, the following devices are used to obtain the target random forest model: a second determination unit, used to obtain a target training set based on a historical feature set of multiple historical objects and a true label corresponding to each historical object; a sampling unit, used to randomly sample the target training set to obtain multiple training subsets; a training unit, used to create multiple decision trees based on multiple training subsets, and train the multiple decision trees based on multiple training subsets to obtain the target random forest model.

[0096] Optionally, in the product recommendation device provided in the embodiment of the present application, the device also includes: a second acquisition unit, used to obtain transaction data information of the target object in a preset time period after recommending the target financial product to the target object; a third acquisition unit, used to obtain transaction volume information of multiple financial products in a preset time period; a third determination unit, used to re-determine the financial product to be recommended based on the transaction data information and the transaction volume information, and recommend the financial product to be recommended to the target object.

[0097] It should be noted that the above-mentioned first acquisition unit 301, first processing unit 302, second processing unit 303 and first determination unit 304 correspond to steps S201 to S204 in the first embodiment, and the four units and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in the first embodiment. It should be noted that the above-mentioned modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned units can also be part of the device and can be run in the computer terminal 10 provided in the first embodiment.

[0098] Example 3

[0099] An embodiment of the present application may provide an electronic device, Figure 4 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (only one is shown) processor 402, memory 404, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0100] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a 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 a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0101] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain initial data information of the target object, wherein the initial data information at least includes the historical transaction data of the target object; obtain a target feature set of the target object based on the initial data information; process the target feature set through a target random forest model to obtain the target object's preference probability value for multiple financial products; determine the target financial product to be recommended based on the preference probability values ​​of the multiple financial products, and recommend the target financial product to the target object.

[0102] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: processing the target feature set through the target random forest model to obtain the target object's preference probability value for multiple financial products, including: voting for multiple financial products based on the target feature set through multiple decision trees in the target random forest model to obtain the number of votes corresponding to each financial product; calculating according to the number of votes corresponding to each financial product to obtain the target object's preference probability value for each financial product.

[0103] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: calculating according to the number of votes corresponding to each financial product to obtain the target object's preference probability value for each financial product, including: calculating according to the number of votes corresponding to each financial product and the number of multiple decision trees to obtain the corresponding proportion value of each financial product; obtaining the historical purchase rate of each financial product; calculating according to the corresponding proportion value of each financial product and the historical purchase rate of each financial product to obtain the preference probability value.

[0104] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: determining the target financial product to be recommended based on the preference probability values ​​of multiple financial products, including: obtaining attribute information of the target object, wherein the attribute information at least includes: the age information and gender information of the target object; constructing a target portrait of the target object based on the attribute information and the preference probability value; determining the target financial product to be recommended based on the target portrait of the target object.

[0105] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: based on the initial data information, obtain the target feature set of the target object, including: preprocessing the initial data information to obtain the target data information; calculating based on the transaction frequency and transaction amount in the target data information to obtain the first feature value; calculating based on the historical financial product information in the target data information to obtain the second feature value; calculating the stability of the target object based on the historical transaction data in the target data information to obtain the third feature value; calculating based on the credit limit information in the target data information to obtain the fourth feature value; obtaining the target feature set based on the first feature value, the second feature value, the third feature value and the fourth feature value.

[0106] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: the target random forest model is obtained by adopting the following steps: a target training set is obtained based on a historical feature set of multiple historical objects and a true label corresponding to each historical object; a target training set is randomly sampled to obtain multiple training subsets; multiple decision trees are created based on the multiple training subsets, and the multiple decision trees are trained based on the multiple training subsets to obtain the target random forest model.

[0107] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: After recommending the target financial product to the target object, the method also includes: obtaining transaction data information of the target object in a preset time period; obtaining transaction volume information of multiple financial products in a preset time period; based on the transaction data information and transaction volume information, re-determining the financial product to be recommended, and recommending the financial product to be recommended to the target object.

[0108] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 4 The structure of the electronic device is not limited. Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations are shown.

[0109] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0110] Example 4

[0111] The embodiment of the present application also provides a computer-readable storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the product recommendation method provided in the first embodiment.

[0112] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0113] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the steps of the product recommendation method.

[0114] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0115] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0116] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0118] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0119] If the integrated unit is implemented in the form of 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 the present application can be essentially or partly or all or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc., which can store program code.

[0120] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A product recommendation method, characterized in that: include: Acquire initial data information of the target object, wherein the initial data information at least includes historical transaction data of the target object; Obtaining a target feature set of the target object according to the initial data information; Processing the target feature set through a target random forest model to obtain the target object's preference probability values ​​for multiple financial products; According to the preference probability values ​​of the plurality of financial products, a target financial product to be recommended is determined, and the target financial product is recommended to the target object.

2. The method according to claim 1, characterized in that The target feature set is processed by the target random forest model to obtain the preference probability values ​​of the target object for multiple financial products, including: Voting for the multiple financial products based on the target feature set using multiple decision trees in the target random forest model to obtain a number of votes corresponding to each financial product; The preference probability value of the target object for each financial product is calculated based on the number of votes corresponding to each financial product.

3. The method according to claim 2, characterized in that The probability value of the target object's preference for each financial product is calculated based on the number of votes corresponding to each financial product, including: Calculate the corresponding proportion of each financial product based on the number of votes for each financial product and the number of the plurality of decision trees; Get the historical purchase rate of each financial product; The preference probability value is calculated based on the corresponding proportion value of each financial product and the historical purchase rate of each financial product.

4. The method according to claim 1, characterized in that Determining the target financial product to be recommended according to the preference probability values ​​of the plurality of financial products includes: Acquire attribute information of the target object, wherein the attribute information at least includes: age information and gender information of the target object; Constructing a target profile of the target object according to the attribute information and the preference probability value; Based on the target profile of the target object, determine the target financial product to be recommended.

5. The method according to claim 1, characterized in that According to the initial data information, a target feature set of the target object is obtained, including: Preprocessing the initial data information to obtain target data information; Calculating according to the transaction frequency and transaction amount in the target data information to obtain a first characteristic value; Calculating according to the historical financial product information in the target data information to obtain a second eigenvalue; Calculating the stability of the target object according to the historical transaction data in the target data information to obtain a third eigenvalue; Calculating according to the credit limit information in the target data information to obtain a fourth eigenvalue; The target feature set is obtained according to the first eigenvalue, the second eigenvalue, the third eigenvalue and the fourth eigenvalue.

6. The method according to claim 1, characterized in that The target random forest model is obtained by following the steps below: According to the historical feature sets of multiple historical objects and the true label corresponding to each historical object, a target training set is obtained; Randomly sampling the target training set to obtain multiple training subsets; Based on the multiple training subsets, multiple decision trees are created, and the multiple decision trees are trained based on the multiple training subsets to obtain the target random forest model.

7. The method according to claim 1, characterized in that After recommending the target financial product to the target object, the method further includes: Obtaining transaction data information of the target object in a preset time period; Obtaining transaction volume information of the plurality of financial products in the preset time period; The financial product to be recommended is determined again based on the transaction data information and the transaction volume information, and the financial product to be recommended is recommended to the target object.

8. A product recommendation device, characterized in that: include: A first acquisition unit, configured to acquire initial data information of a target object, wherein the initial data information at least includes historical transaction data of the target object; A first processing unit, configured to obtain a target feature set of the target object according to the initial data information; A second processing unit is used to process the target feature set through a target random forest model to obtain the preference probability values ​​of the target object for multiple financial products; The first determining unit is configured to determine a target financial product to be recommended according to the preference probability values ​​of the plurality of financial products, and recommend the target financial product to the target object.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the computer-readable storage medium is located is controlled to execute the product recommendation method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the product recommendation method described in any one of claims 1 to 7.

Images