Research on stock recommendation system based on improved collaborative filtering

This paper proposes a stock recommendation model based on improved collaborative filtering by integrating investor-stock interaction data into the similarity calculation process of traditional collaborative filtering recommendation systems. Experimental comparisons were made with recommendation algo...

Full description

Saved in:
Bibliographic Details
Published in2023 International Conference on Computer, Internet of Things and Smart City (CIoTSC) pp. 186 - 192
Main Authors Duan, Ganglong, Yang, Xinjun
Format Conference Proceeding
LanguageEnglish
Published IEEE 03.11.2023
Subjects
Accuracy
Association rule learning
Collaborative filtering
Correlation coefficient
Data models
Information filters
Internet of Things
Recommender systems
Similarity calculation
Smart cities
Stock recommendation
Online AccessGet full text

Cover

More Information
Summary:This paper proposes a stock recommendation model based on improved collaborative filtering by integrating investor-stock interaction data into the similarity calculation process of traditional collaborative filtering recommendation systems. Experimental comparisons were made with recommendation algorithms based on association rules, text content, and traditional collaborative filtering. The results show that the improved collaborative filtering stock recommendation method has higher accuracy, recall rate, and Matthews correlation coefficient (MCC) at different recommendation lengths, thereby verifying the effectiveness of the proposed stock recommendation model.
DOI:10.1109/CIoTSC60428.2023.00038