Leveraging Grey Wolf Optimization for Multi-Criteria Recommender Systems

Traditional recommender system makes recommendations to users based on their preferences by utilising overall ratings. However, these recommendations do not accurately reflect the taste of the user. Therefore, inclusion of various criteria ratings into recommender system may be helpful to generate effective recommendations which may reflect accurately user preferences. However,forfeiting the optimal weights of various users on different criteria is a major concern in multi-criteria recommender system. In our proposed work we have employed the capability of grey wolf optimization to find out optimal weights of various users on different criteria and conducted exhaustive empirical study on the ITM-Rec dataset to support our proposed work. Experimental results demonstrate the superiority of our work in terms of various performance measures.