Fuzzy electromagnetic optimisation clustering algorithm for collaborative filtering

ABSTRACT

In this paper, an attempt is made to improve the performance of fuzzy c-means (FCM) clustering by incorporating in it the concepts of Electromagnetic Force Optimisation (EFO).EFO is a recently proposed metaheuristic for global optimisation. Its integration with FCM helps in minimising the shortcomings of FCM by providing a good initial start and eventually in determining efficient clusters. The proposed method, named fuzzy electromagnetic clustering, is tested on MovieLens data set. Simulation results demonstrate that the proposed algorithm outperforms the conventional methods available in literature in terms of RMSE and MAE metrics.

KEYWORDS:

• Recommender system
• clustering
• collaborative filtering
• electromagnetic field
• optimisation
• metaheuristic

Disclosure statement

No potential conflict of interest was reported by the authors.