Offline Evaluation of Recommender Systems in a User Interface With Multiple Carousels

Many video-on-demand and music streaming services provide the user with a page consisting of several recommendation lists, i.e., widgets or swipeable carousels, each built with specific criteria (e.g., most recent, TV series, etc.). Finding efficient strategies to select which carousels to display is an active research topic of great industrial interest. In this setting, the overall quality of the recommendations of a new algorithm cannot be assessed by measuring solely its individual recommendation quality. Rather, it should be evaluated in a context where other recommendation lists are already available, to account for how they complement each other. The traditional offline evaluation protocol however does not take this into account. To address this limitation, we propose an offline evaluation protocol for a carousel setting in which the recommendation quality of a model is measured by how much it improves upon that of an already available set of carousels. We also propose to extend ranking metrics to the two-dimensional carousel setting in order to account for a known position bias, i.e., users will not explore the lists sequentially, but rather concentrate on the top-left corner of the screen. Finally, we describe and evaluate two strategies for the ranking of carousels in a scenario where the technique used to generate the two-dimensional layout is agnostic on the algorithms used to generate each carousel. We report experiments on publicly available datasets in the movie domain to show how the relative effectiveness of several recommendation models compares. Our results indicate that under a carousel setting the ranking of the algorithms changes sometimes significantly. Furthermore, when selecting the optimal carousel layout accounting for the two dimensional layout of the user interface leads to very different selections.