Collaborative filtering and kNN based recommendation to overcome cold start and sparsity issues: A comparative analysis

Collaborative Filtering (CF) has intrigued several researchers whose goal is to enhance Recommender System's performance by mitigating their drawbacks. CF's common idea is to recognize user's preferences by considering their ratings given to the items. The best-known limitations of recommender systems are the cpld start and data sparsity. In this paper, we analyse the CF-based recommendation approaches used to overcome the 2 issues, viz. cold start and data sparsity. This work attempts to implement the recommendation systems by 1) Generating a user-item similarity matrix and prediction matrix by performing collaborative filtering using memory-based CF approaches viz. KNNBasic, KNNBaseline, KNNWithMeans, SVD, and SVD++. 2) Generating a user-item similarity matrix and prediction matrix by performing collaborative filtering using model-based CF approach viz. Co-Clustering. The results reveal that the CF implemented using the K-NNBaseline approach decreased error rate when applied to MovieTrust datasets using cross-validation (CV = 5, 10, and 15). This approach is proved to address the cold start, sparsity issues and provide more relevant items as a recommendation.