Financial product recommendation method and system, storage medium and equipment

Abstract

The invention belongs to the field of financial product recommendation, and provides a financial product recommendation method and system, a storage medium and equipment. The method comprises the following steps: acquiring financial management user data; obtaining a recommended financial management product type based on financial management user data and a trained self-encoding neural network model, wherein the training process of the self-coding neural network model comprises the following steps of: pre-training a self-coding neural network model by adopting financial management user data; and splicing the financial management user data and the plurality of nearest neighbor data to form training data; and taking parameters in the pre-trained self-encoding neural network model as initial values, and continuously training the self-encoding neural network model by using the training data until the maximum number of iterations is reached or the loss error is smaller than a stop threshold.

Description

technical field [0001] The invention belongs to the field of wealth management product recommendation, and in particular relates to a wealth management product recommendation method, system, storage medium and equipment. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With the rapid development of 5G, the number and attributes of samples have increased sharply, such as the sum analysis and evaluation of financial development, including user basic information, different credit ratings, working years, transaction types, etc. Different policies need to be adopted for different regions to make economic development more balanced. Faced with such a huge amount of data and high attributes, and the hidden features of the sample are no longer obvious, it is difficult for traditional clustering algorithms to process such data. Deep neural networks...

AI Technical Summary

Problems solved by technology

[0004] Although the deep neural network can extract the deep feature information of high-attribute samples, which is very helpful for data mining, most of the current deep clustering algorithms only focus on the global structure of the financial data of the target user, and do not consider the financial data samples of the target user. The effective information of local similarity is insufficient for the clustering result division of the target user's financial boundary data points; and the affinity matrix between the target user's financial data samples is a very important measure of the neighbor standard, initialized Insufficient precision will also have a great impact on the clustering results of the target user group, making it impossible to recommend accurate financial products for users

Images