RegionKNN: A Scalable Hybrid Collaborative Filtering Algorithm for Personalized Web Service Recommendation
Authors:
- Xi ChenXCXi Chen
- Xudong LiuXLXudong Liu
- Zicheng HuangZHZicheng Huang
- Hailong SunHSHailong Sun
Top Cited Papers
- 1 July 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9-16
Abstract
Several approaches to web service selection and recommendation via collaborative filtering have been studied, but seldom have these studies considered the difference between web service recommendation and product recommendation used in e-commerce sites. In this paper, we present RegionKNN, a novel hybrid collaborative filtering algorithm that is designed for large scale web service recommendation. Different from other approaches, this method employs the characteristics of QoS by building an efficient region model. Based on this model, web service recommendations will be generated quickly by using modified memory-based collaborative filtering algorithm. Experimental results demonstrate that apart from being highly scalable, RegionKNN provides considerable improvement on the recommendation accuracy by comparing with other well-known collaborative filtering algorithms.Keywords
This publication has 12 references indexed in Scilit:
- WSRec: A Collaborative Filtering Based Web Service Recommender System2009
- Non-intrusive monitoring and service adaptation for WS-BPEL2008
- Personalized QoS Prediction forWeb Services via Collaborative Filtering2007
- A Web Service Recommender System Using Enhanced Syntactical Matching2007
- A collaborative filtering algorithm and evaluation metric that accurately model the user experience2004
- IntroductionCommunications of the ACM, 2003
- Amazon.com recommendations: item-to-item collaborative filteringIEEE Internet Computing, 2003
- MovieLens unplugged2003
- GroupLensCommunications of the ACM, 1997
- User Modeling via Stereotypes*Cognitive Science, 1979