MCARS-CC: A Scalable Multi-context-aware Recommender System

Recommendation Systems (RSs) have proved a compelling performance to overcome the data overload problem. Context-aware recommenders guide users/clients to more personalized recommendations. Incorporating contextual features in recommendation systems improves the systems' accuracy; however, they still suffer from sparsity and scalability problems which impact the quality of recommendations. To overcome these limitations, we propose a multi-context-aware recommendation system using the notion of consensus clustering, named MCARS-CC. Experimental results on real-world datasets show that the concept of consensus learning using clustering analysis can significantly improve the recommender systems' accuracy, handle sparsity in data, and address scalability for large-scale datasets. The proposed method surpasses the other recommendation algorithms in terms of accuracy, precision and recall. The MAE and RMSE results show that consensus clustering leads to better accuracy measures and a more stable resilient recommendation system; in particular, incorporating Hyber-Graph with Partitioning (HGPA) Consensus has improved MAE and RMSE by 25.96% and 8.94%, respectively, in Yelp-Dataset.