Collaborative Filtering: A Comparison of Graph-based Semisupervised Learning Methods and Memory-based Methods

Abstract

Collaborative filtering is a method of making predictions about the interests of a user based on interest similarity to other users and consequently recommending the predicted items. There is a widespread use of collaborative filtering systems in commercial websites, such as Amazon.com, which has popularized item-based methods. There are also many music and video sites such as iLike and Everyone’s a Critic (EaC) that implement collaborative filtering systems. This trend is growing in product-based sites. This paper discusses the implementation of graph-based semisupervised learning methods and memory-based methods to the collaborative filtering scenario and compares these methods to baseline methods such as techniques based on weighted average. This work compares the predictive accuracy of these methods on the MovieLens data set. The metrics used for evaluation measure the accuracy of generated predictions based on already known, held-out ratings that constitute the test set. Preliminary results indicate that graph-based semi-supervised learning methods perform better than baseline methods. However, some of the memory-based methods outperform the graph-based semi-supervised learning methods as well as the baseline methods.