Share Email Print
cover

Proceedings Paper

An optimized item-based collaborative filtering recommendation algorithm based on item genre prediction
Author(s): De-Jia Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

With the fast development of Internet, many systems have emerged in e-commerce applications to support the product recommendation. Collaborative filtering is one of the most promising techniques in recommender systems, providing personalized recommendations to users based on their previously expressed preferences in the form of ratings and those of other similar users. In practice, with the adding of user and item scales, user-item ratings are becoming extremely sparsity and recommender systems utilizing traditional collaborative filtering are facing serious challenges. To address the issue, this paper presents an approach to compute item genre similarity, through mapping each item with a corresponding descriptive genre, and computing similarity between genres as similarity, then make basic predictions according to those similarities to lower sparsity of the user-item ratings. After that, item-based collaborative filtering steps are taken to generate predictions. Compared with previous methods, the presented collaborative filtering employs the item genre similarity can alleviate the sparsity issue in the recommender systems, and can improve accuracy of recommendation.

Paper Details

Date Published: 11 July 2009
PDF: 5 pages
Proc. SPIE 7490, PIAGENG 2009: Intelligent Information, Control, and Communication Technology for Agricultural Engineering, 74901I (11 July 2009); doi: 10.1117/12.836808
Show Author Affiliations
De-Jia Zhang, Wenzhou Vocational and Technical College (China)


Published in SPIE Proceedings Vol. 7490:
PIAGENG 2009: Intelligent Information, Control, and Communication Technology for Agricultural Engineering
Honghua Tan; Qi Luo, Editor(s)

© SPIE. Terms of Use
Back to Top