A New User Similarity Measure for Collaborative Filtering Algorithm
Authors:
- Lei ShenLSLei Shen
- Yiming ZhouYZYiming Zhou
- 1 January 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 375-379
Abstract
This paper proposes a new user similarity measure to improve the collaborative filtering algorithm. We apply a basic fractional function and an exponential function to calculate the similarity between users by taking both common features and different features into consideration. We test our two measures on two data sets, movie lens and book-crossing data sets. Experiment results show that our basic fractional function slightly improves the performance, while exponential function significantly outperforms other similarity measures.Keywords
This publication has 9 references indexed in Scilit:
- A new similarity measure for collaborative filtering to alleviate the new user cold-starting problemInformation Sciences, 2008
- Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensionsIEEE Transactions on Knowledge and Data Engineering, 2005
- Evaluating collaborative filtering recommender systemsACM Transactions on Information Systems, 2004
- Feature Weighting and Instance Selection for Collaborative Filtering: An Information-Theoretic Approach*Knowledge and Information Systems, 2003
- Evaluation of Item-Based Top-N Recommendation Algorithms2001
- Personalization of Supermarket Product RecommendationsData Mining and Knowledge Discovery, 2001
- Analysis of recommendation algorithms for e-commerce2000
- GroupLens1994
- Features of similarity.Psychological Review, 1977