# A Methodology for the Offline Evaluation of Recommender Systems in a User Interface with Multiple Carousels

arXiv: https://arxiv.org/abs/2105.06275 · HTML: https://mlsanity.com/paper/2105.06275/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 20 references that are in the map.
- First posted on arXiv 13 May 2021.

## Builds on (most cited first, 5 of 5)

- [Embarrassingly Shallow Autoencoders for Sparse Data](https://mlsanity.com/paper/1905.03375/) (2019)
- [A Troubling Analysis of Reproducibility and Progress in Recommender Systems Research](https://mlsanity.com/paper/1911.07698/) (2019)
- [Carousel Personalization in Music Streaming Apps with Contextual Bandits](https://mlsanity.com/paper/2009.06546/) (2020)
- [ContentWise Impressions: An Industrial Dataset with Impressions Included](https://mlsanity.com/paper/2008.01212/) (2020)
- [Learning Representations of Hierarchical Slates in Collaborative Filtering](https://mlsanity.com/paper/2010.06987/) (2020)

## Abstract (arXiv)

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 a specific criterion (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. This is not considered by traditional offline evaluation protocols. Hence, 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 report experiments on publicly available datasets on the movie domain and notice that under a carousel setting the ranking of the algorithms change. In particular, when a SLIM carousel is available, matrix factorization models tend to be preferred, while item-based models are penalized. We also propose to extend ranking metrics to the two-dimensional carousel layout 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.