Product recommendation method, product recommendation system and computer readable storage medium

Abstract

The embodiment of the invention provides a product recommendation method and a product recommendation system, and the method comprises the steps: obtaining the historical transaction data of a target user to build a sample set, wherien the sample set comprises a training set and a verification set; obtaining a product of a target user, and extracting a plurality of user attribute features and a plurality of product attribute features of the target user from the product to form a combined feature; establishing a plurality of evaluation models on the basis of the training set and the combined features, and screening one evaluation model from the test set as a product scoring model; and scoring and sorting the multiple types of products in the to-be-predicted set according to the product scoring model, screening out the to-be-recommended products, and recommending the to-be-recommended products to the target user in the to-be-recommended time interval. According to the product recommendation method and system, the product with the best matching degree with the user can be analyzed according to the historical transaction data and the combined features of the user, the product is adaptively recommended for the target user, and the recommendation accuracy and the conversion rate are improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a product recommendation method, a product recommendation system and a computer-readable storage medium. Background technique [0002] With the rapid development of the financial industry, many financial institutions currently recommend some financial products to be promoted to users, such as funds and securities. However, the recommended products must conform to the user's consumption concepts and habits to increase the conversion rate. Currently, several commonly used recommendation methods include: randomly recommending funds to users, recommending funds to users in full, and recommending funds to users without a strategy. Recommending funds to users randomly refers to recommending any fund products to users, which will lead to a low conversion rate of fund recommendation display positions; full recommendation to users is to provide all fund products to users withou...

AI Technical Summary

Problems solved by technology

Recommending funds to users randomly refers to recommending any fund products to users, which will lead to a low conversion rate of fund recommendation display positions; full recommendation to users is to provide all fund products to users without screening, which may lead to users choosing There are too many types of products, and funds cannot be used and turned over in a timely manner; in addition, recommendations without strategies can easily lead to a decrease in the efficiency of fund recommendations

[0003] Therefore, the currently used product recommendation methods have great limitations, and cannot select suitable products for users, resulting in ineffective use of funds

Images