Multi-objective optimization for location-based and preferences-aware recommendation

Abstract

Location is of vital importance in recommender systems. This paper proposes a novel multi-objective framework for location-based and preference-aware recommendation. Under this framework, location-based recommendation is modeled as a multiobjective optimization problem and two contradictory objective functions are taken into consideration. One objective function aims to depict the performance of recommendation algorithm to recommend similar items. Another objective function reflects the ability of recommendation algorithm to recommend diverse items. It is a challenge to optimize these two contradictory objective functions simultaneously. In this paper, a novel multi-objective evolutionary algorithm is proposed to solve this modeled multiobjective optimization problem. The proposed algorithm can return a series of high-quality recommendation candidate solutions in one run and every solution is a trade-off between these two objective functions. The proposed algorithm is applied on two real recommendation scenarios: movie recommendation and music recommendation. Experimental results show that the proposed algorithm can produce recommendation solutions which are much better than those produced by existing algorithms in location-based recommendation and the proposed algorithm also has great performance in alleviating data sparsity and cold-start problems.