XGBoost financial product recommendation method based on customer information completion

A financial product and customer information technology, applied in finance, resources, marketing, etc., can solve the problem of low accuracy of product recommendation results, achieve accurate recommendation results, comprehensive index system, and improve accuracy

Pending Publication Date: 2021-06-22
JIANGSU INST OF ECONOMIC & TRADE TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The above method does not make a reasonable estimate of the missing information, resulting in inaccurate product recommendation results obtained in the case of missing information

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • XGBoost financial product recommendation method based on customer information completion
  • XGBoost financial product recommendation method based on customer information completion
  • XGBoost financial product recommendation method based on customer information completion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Such as figure 1 As shown, the method for recommending financial products with missing information in the present invention includes the following steps:

[0024] (10) Establishment of the model index system: Based on the business transaction data between the enterprise and the bank, a recommended model index system is established, and the index items include customer financial data and customer non-financial data;

[0025] (20) Sample set construction: According to the model index system, customer information is collected, and the recommendation model training sample set and test sample set are constructed.

[0026] For example, take the collected historical data of financial indicators as sample data. According to Table 1 and Table 2, 33 financial indicators and 6 non-financial indicators are selected to form the 39-dimensional feature vector of the recommendation model. The data of 6,000 companies are randomly selected as training samples, and the data of 1,500 comp...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an XGBoost financial product recommendation method based on customer information complementation, which is high in recommendation result accuracy. The method comprises the following steps: (10) establishing of a model index system: establishing a recommendation model index system according to business exchange data of an enterprise and a bank; (20) sample set construction: collecting customer information according to the model index system, and constructing a recommendation model training sample set and a test sample set; (30) customer information completion: estimating missing information based on a low-rank matrix completion method of a singular value threshold method, and completing customer information; (40) recommendation model acquisition: training the XGBoost model by using the recommendation model training sample set, and testing the trained XGBoost model by using the recommendation model test sample set to obtain a recommendation model; (50) financial product recommendation: according to the information of the target customer, utilizing the recommendation model to recommend financial products.

Description

technical field [0001] The invention belongs to the technical field of bank financial product recommendation, in particular to an XGBoost financial product recommendation method based on customer information completion with high recommendation result accuracy. Background technique [0002] Under the business philosophy of providing personalized services to customers, commercial banks have launched a wide variety of financial service products. However, the large number of products and the continuous introduction of new services make it difficult for customers to keep abreast of and make reasonable choices. In addition, not selectively recommending financial products will not only make it difficult for customers to choose, but also cause a waste of resources. How to recommend products with a high degree of coincidence with customer needs in a targeted manner according to the characteristics of customers is an effective means for banks to improve service efficiency and custome...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q30/06G06Q30/02G06Q10/06G06Q40/02
CPCG06Q30/0631G06Q30/0202G06Q10/06393G06Q10/067G06Q40/02
Inventor 周遊李鑫汝刚蒋群艳
Owner JIANGSU INST OF ECONOMIC & TRADE TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap