Note:  The research presented in this paper is not connected with the current affiliation of Thomas Hornung and Cai-Nicolas Ziegler.
Abstract: Taste in music is of highly subjective nature, making the recommending of music tracks a challenging research task. With TRECS, our live prototype system, we present a weighted hybrid recommender approach that amalgamates three diverse recommender techniques into one comprehensive score. Moreover, our prototype system peppers the generated result list by some simple serendipity heuristic. This way, users can benefit from recommendations aligned with their current taste in music while gaining some exploratory diversification. Empirical evaluations of the live TRECS system, based on an online evaluation, assess the overall recommendation quality as well as the impact of each of the three sub-recommenders. In addition, to better understand the nature and impact of serendipity in isolation, we conducted another study with another recommender prototype of ours, named SONG STUMBLER. The latter assesses three different serendipity metrics in an online evaluation.
Keywords: Music recommender, hybrid recommender, serendipity, empirical evaluation, recommendation quality