An Ethical Multi-Stakeholder Recommender System Based on Evolutionary Multi-Objective Optimization
Naime Ranjbar Kermany, Weiliang Zhao, Jian Yu Yang, Jia Xin Wu, Luiz Augusto Sangoi Pizzato · 2020
In this work, we propose an ethical multi-stakeholder recommender system that uses a multi-objective evolutionary algorithm to make a trade-off between provider coverage, long-tail services inclusion, and recommendation accuracy. Experimental results on real-world datasets show that the proposed method significantly improves the novelty and diversity of recommended services and the coverage of providers with minor loss of accuracy.