Enhancing the long-term performance of recommender system

Abstract

Recommender system is a critically important tool in online commercial system and provide users with personalized recommendation 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 behaviour. The result shows that not only long-term recommendation accuracy can be enhanced significantly but the diversity of item in online system maintains healthy. Notably, an optimal parameter n * of ARL existed in long-term recommendation, indicating that there is a trade-off between keeping 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 evolving network, which reveals the robustness of ARL method.

Fair ranking: a critical review, challenges, and future directions

“…For example, studies on spillover effects can not proceed without the data on complementary and associated services. These data and legal bottlenecks might have also contributed to the fact that there are very few works exploring this direction, and out of the limited works, some are limited to either theoretical analysis [114,15] or simulations with assumed parametrizations [176,61,163] in absence of complementary data. 5 We discuss these bottlenecks in Section 4.2 and Section 4.3.…”