A Load Balanced Recommendation Approach

TL;DR

This paper introduces Load Balanced Recommender System (LBRS), a novel approach inspired by wireless sensor network algorithms, which improves recommendation accuracy and diversity while addressing scalability and interpretability issues in traditional methods.

Contribution

The paper proposes a new probabilistic recommendation scheme that incorporates item importance and heterogeneity, along with a novel diversity metric, inspired by cluster head selection algorithms.

Findings

LBRS outperforms baseline methods in simulation studies.

Incorporating item importance enhances recommendation accuracy.

The new diversity metric considers intra-list and between-list diversity.

Abstract

Recommender systems (RSs) are software tools and algorithms developed to alleviate the problem of information overload, which makes it difficult for a user to make right decisions. Two main paradigms toward the recommendation problem are collaborative filtering and content-based filtering, which try to recommend the best items using ratings and content available. These methods typically face infamous problems including cold-start, diversity, scalability, and great computational expense. We argue that the uptake of deep learning and reinforcement learning methods is also questionable due to their computational complexities and uninterpretability. In this paper, we approach the recommendation problem from a new prospective. We borrow ideas from cluster head selection algorithms in wireless sensor networks and adapt them to the recommendation problem. In particular, we propose Load Balanced Recommender System (LBRS), which uses a probabilistic scheme for item recommendation. Furthermore, we factor in the importance of items in the recommendation process, which significantly improves the recommendation accuracy. We also introduce a method that considers a heterogeneity among items, in order to balance the similarity and diversity trade-off. Finally, we propose a new metric for diversity, which emphasizes the importance of diversity not only from an intra-list perspective, but also from a between-list point of view. With experiments in a simulation study performed on RecSim, we show that LBRS is effective and can outperform baseline methods.