Evaluating the Relative Performance of Neighbourhood-Based Recommender Systems

Neighbourhood-based recommender systems are a class of collaborative filtering algorithms, which rely on finding like-minded users to generate recommendations, automating what is usually known as word-of-mouth. These systems attempt to solve the information overload problem by presenting the user with relevant items. However, there is evidence showing that these algorithms may contribute to the filter bubble problem, making it harder for the user to find interesting items which are non-popular. In this paper we propose a novel evaluation of the performance and biases of the two most common neighbourhood-based approaches: user k-nearest neighbour collaborative filtering (UKNN ), and item k-nearest neighbour collaborative filtering (IKNN). We propose an evaluation which considers the size of the neighbourhood, finding that optimising for accuracy in UKNN algorithms leads to a poor performance in terms of diversity, a higher bias towards popularity, and less unique recommendations, when compared to the IKNN approach.