Hybrid Recommendation: Combining Content-Based Prediction and Collaborative Filtering

Abstract

Recommender systems improve access to relevant products and information by making personalized suggestions based on historical data of user’s likes and dislikes. They have become fundamental application in electronic commerce and information access, provide suggestions that effective prune large information spaces so that users are directed toward those item that best meet their needs and preferences. Collaborative filtering and content-based recommending are two fundamental techniques that have been proposed for performing recommendation. Both techniques have their own advantages however they cannot perform well in many situations. To improve performance, various hybrid techniques have been considered. This paper proposes a framework to improve the recommendation performance by combining content-based prediction based on Support Vector Machines and conventional collaborative filtering. The experimental results show that SVMs can improve the performance of the recommender system.