Auralist

TLDR

Recommendation systems help users discover content, and an ideal system should emulate a trusted friend by balancing accuracy, diversity, novelty, and serendipity. This work introduces the Auralist framework, designed to simultaneously balance and improve accuracy, diversity, novelty, and serendipity. Auralist employs novel algorithms inspired by serendipitous discovery to inject serendipity, novelty, and diversity into recommendations while minimizing accuracy loss. Quantitative evaluation and a music recommendation user study show that Auralist’s emphasis on serendipity increases user satisfaction.

Abstract

Recommendation systems exist to help users discover content in a large body of items. An ideal recommendation system should mimic the actions of a trusted friend or expert, producing a personalised collection of recommendations that balance between the desired goals of accuracy, diversity, novelty and serendipity. We introduce the Auralist recommendation framework, a system that - in contrast to previous work - attempts to balance and improve all four factors simultaneously. Using a collection of novel algorithms inspired by principles of "serendipitous discovery", we demonstrate a method of successfully injecting serendipity, novelty and diversity into recommendations whilst limiting the impact on accuracy. We evaluate Auralist quantitatively over a broad set of metrics and, with a user study on music recommendation, show that Auralist's emphasis on serendipity indeed improves user satisfaction.