An optimized item-based collaborative filtering algorithm

Abstract

Collaborative filtering over the years have emerged as an alternative recommender system to address some of the setbacks of content based filtering. Although, Collaborative filtering has offered some benefits to the majority of the online stores in recommending products to users using users’ ratings of similarity measure, its usage has also raised some doubt in the minds of researchers, regarding its effectiveness in handling ratings with limited number of users or no rating record from users. Thus, this has resulted in efforts by researchers in determining further ways to combat the issues attributed with the existing collaborative filtering techniques in terms of data sparsity or cold-start situations. This study focused on improving the traditional similarity measurements that currently exist on the item-based collaborative filtering, in order to accommodate and mitigate further the issue of cold-start situations. Thus, this study proposed an algorithm which is meant to balance the three current traditional measurement metrics such as: Cosine-based similarity, Pearson correlation similarity and Adjusted cosine similarity, in the direction of cold-start situations. The improved algorithm of traditional measurement metrics were further compared with the existing algorithm of the traditional metrics. Results showed that the proposed algorithm offered a better item-based collaborative filtering algorithm to recommendation systems than the existing, using data set from Movielens recommender system. Hence, the proposed algorithm did not only mitigate the drawbacks experienced with the three traditional algorithms in terms of data sparsity or cold-start situations but also retained the good features of the existing item-based collaborative filtering algorithm. Thus, the proposed algorithm complemented the strength of the three traditional measurement metrics with evidence shown when measured with Mean Absolute Error.