Financial product recommendation method based on GAMxNN model
A technology for recommending methods and models, applied in data processing applications, instruments, finance, etc., and can solve the problems of high accuracy, low interpretability, high interpretability, and low accuracy of data prediction.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0071] The method of the present invention will be further described below in conjunction with the accompanying drawings and preferred specific embodiments of the present invention.
[0072] Such as Figure 1 to Figure 3 As shown, the present invention is a method for recommending financial products based on the GAMxNN model, which specifically includes the following steps:
[0073] The first step is data cleaning and preprocessing; cleaning and preprocessing of customer data who have recommended target financial products in the past 2 years, including consistency check, removing duplicate data, abnormal data and invalid data, filling missing values with 0, And do standardization and normalization processing, in addition, the categorical variables need to be converted into numerical variables.
[0074] For example: the data structure after data cleaning and preprocessing is: the target variable y is a binary classification variable, and the value of 1 or 0 indicates the suc...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com