Enhancing the long-term performance of recommender system

The recommender system is a critically important tool in the online commercial system and provides users with personalized recommendations on items. So far, numerous recommendation algorithms have been made to further improve the recommendation performance in a single-step recommendation, while the long-term recommendation performance is neglected. In this paper, we proposed an approach called Adjustment of Recommendation List (ARL) to enhance the long-term recommendation accuracy. In order to observe the long-term accuracy, we developed an evolution model of network to simulate the interaction between the recommender system and user’s behavior. The result shows that not only long-term recommendation accuracy can be enhanced significantly but the diversity of items in an online system maintains healthy. Notably, an optimal parameter n∗ of ARL existed in the long-term recommendation, indicating that there is a trade-off between keeping the diversity of item and user’s preference to maximize the long-term recommendation accuracy. Finally, we confirmed that the optimal parameter n∗ is stable during the evolving network, which reveals the robustness of the ARL method.