International Journal of Mathematics And Computer Research

Abstract

The new user cold start issue represents a serious problem in recommender systems as it can lead to the loss of new users who decide to stop using the system due to the lack of accuracy in the recommendations received in that first stage in which they have not yet cast a significant number of votes with which to feed the recommender system’s collaborative filtering core. For this reason it is particularly important to design new similarity metrics which provide greater precision in the results offered to users who have cast few votes. The possible solutions, now in days, are profile expansion and developing a new method of finding similarity between existing users. In this paper, we focus on both of these methods. The metric has been tested on the Netflix and Movielens databases, obtaining important improvements in the measures of accuracy, precision and recall when applied to new user cold start situations. The profile expansion technique is proposed and evaluated by three kinds of techniques: item-global, item-local and user-local. These techniques are also tested on the Netflix and Movielens database. The results obtained by both the techniques are good and we can use that for our future work.