What is the Value of Rating Obscure Items? An Analysis of the Effect of Less-Popular Items on Recommendation Quality

Abstract

Recommender systems designers believe that the system stands to benefit from the users rating items that do not have many ratings. However, the effect of this act of rating lesser known items on the user’s recommendations is unknown. This leads to asking the question of whether these low popularity items affect the recommendations received by users. This work looks at the effect less popular items have on a user’s recommendations and the prediction and recommendations metrics that quantify the quality of recommendations. Using a matrix factorization model to build a recommender system, we modify a subset of users’ ratings data and look at the difference in recommendations generated. We also make use of popular recommender systems metrics such as nDCG, Precison and Recall to evaluate the effect of these modifications.Apart from looking at the ef- fect of this ”truncation” of casual user ratings data on the casual users themselves, we also look at the effects of this ”truncation” on the more invested users of the system, in terms of top-n recommendation and prediction metrics. The results of these evalu- ations appear promising, with very little to no loss of information, personalization or metric scores for more casual users. The results of these evaluations for more serious users also appears to have little effect on the performance of top-n recommendation and prediction metrics.