On Unexpectedness in Recommender Systems

TLDR

Recommender systems have achieved broad social and business success, yet user satisfaction remains insufficient, highlighting unexpectedness as a key dimension for improvement. This article proposes a utility‑theory‑based method to enhance user satisfaction by generating unexpected recommendations. The authors formalize unexpectedness, distinguish it from novelty, serendipity, and diversity, and present mechanisms for modeling user expectations, metrics for measuring unexpectedness, and an algorithm that delivers high‑quality, hard‑to‑discover recommendations aligned with user interests. Experiments on real‑world datasets show that the proposed approach surpasses baseline methods in unexpectedness, coverage, aggregate diversity, and dispersion while maintaining accuracy.

Abstract

Although the broad social and business success of recommender systems has been achieved across several domains, there is still a long way to go in terms of user satisfaction. One of the key dimensions for significant improvement is the concept of unexpectedness . In this article, we propose a method to improve user satisfaction by generating unexpected recommendations based on the utility theory of economics. In particular, we propose a new concept of unexpectedness as recommending to users those items that depart from what they would expect from the system - the consideration set of each user. We define and formalize the concept of unexpectedness and discuss how it differs from the related notions of novelty, serendipity, and diversity. In addition, we suggest several mechanisms for specifying the users’ expectations and propose specific performance metrics to measure the unexpectedness of recommendation lists. We also take into consideration the quality of recommendations using certain utility functions and present an algorithm for providing users with unexpected recommendations of high quality that are hard to discover but fairly match their interests. Finally, we conduct several experiments on “real-world” datasets and compare our recommendation results with other methods. The proposed approach outperforms these baseline methods in terms of unexpectedness and other important metrics, such as coverage, aggregate diversity and dispersion, while avoiding any accuracy loss.