Improving the quality of the personalized collaborative filtering recommendation approach employing folksonomy method

Abstract

Popular E-commerce systems such as Amazon and eBay require customer personal data to be stored on their servers for serving these customers with personalized recommendations. Collaborative filtering is one of the most successful technologies for building personalized recommender systems, and is extensively used in many personalized E-commerce systems. However, existing collaborative filtering algorithms have been suffering from data sparsity and scalability problems which lead to inaccuracy of recommendation. With the increase of customers and commodities, the customer rating data is extremely sparse, which leads to the low efficient collaborative filtering E-commerce recommendation system. To address these issues, many approaches of processing no-rated items in collaborative filtering recommendation algorithm have been proposed. In order to improve the quality of the personalized collaborative filtering recommendation, an item-based collaborative filtering approach employing folksonomy method is given. The approach uses the folksonomy technology to fill the no-rated items in the collaborative filtering recommendation algorithm. © 2012 Springer-Verlag GmbH.