Bank financing product recommendation method based on combination of generalized additive model and matrix decomposition

Abstract

The invention discloses a bank financial product recommendation method based on a generalized additive model combined with matrix decomposition, relates to the technical field of data processing in abank financial product management system, and solves the technical problem that an existing bank financial product recommendation method has no interpretability or is poor in precision, and the bank financial product recommendation method comprises the steps of 1, performing feature extraction processing on data; dividing the original input into user information, product information and behavior information; 2, respectively establishing generalized additive models for the user information and the product information; 3, performing matrix decomposition fitting on the user behavior information for the residual part; 4, repeating the steps 2 to 3 by adopting an iterative method until the model converges; and step 5, obtaining a final prediction result by combining the generalized additive model and the matrix decomposition model. On the premise of ensuring high recommendation precision, various model explanations of a linear part and a matrix decomposition part can be given. The problem of maximum cold start of an existing recommendation system is solved. Therefore, the recommendation credibility of the user is improved, and the recommendation quality is improved.

Description

technical field [0001] The invention relates to the technical field of data processing in a bank wealth management product management system, in particular to a method for recommending and processing bank wealth management products. Background technique [0002] With the advent of the era of big data, precision marketing is becoming more and more important in today's society, and it has a huge role and development potential in the banking and financial industry. However, one of the most important links in precision marketing is personalized recommendation. By giving different recommended content to different users, it can increase the user effect rate while reducing marketing costs. [0003] Although today's personalized recommendation algorithms, such as deep learning algorithms such as DeepFM, can obtain better accuracy, that is, they can better capture historical behavior information of users in the past, there is a problem that the recommendation results cannot be explai...

AI Technical Summary

Problems solved by technology

[0005] In summary, the purpose of the present invention is to solve the technical problems of current bank wealth management product recommendation methods that are either unexplainable or poor in accuracy, and propose a bank wealth management product recommendation method based on a generalized additive model combined with matrix decomposition , while ensuring high precision, it provides model interpretability, which can improve the user's credibility of the model, so as to improve the practicality of personalized recommendation

Images