MTS Kion Implicit Contextualised Sequential Dataset for Movie Recommendation

TL;DR

This paper introduces a new implicit interaction-based movie recommendation dataset from MTS Kion, enriched with contextual and demographic data, and discusses a related recommender systems challenge with open benchmarking.

Contribution

The paper provides a novel dataset based on implicit user interactions with rich contextual information, and details a competitive benchmark for developing improved recommendation algorithms.

Findings

Dataset includes implicit interactions, contextual info, and user demographics.

The MTS Kion Challenge fosters development of advanced recommender systems.

Open sandbox allows researchers to test and compare algorithms.

Abstract

We present a new movie and TV show recommendation dataset collected from the real users of MTS Kion video-on-demand platform. In contrast to other popular movie recommendation datasets, such as MovieLens or Netflix, our dataset is based on the implicit interactions registered at the watching time, rather than on explicit ratings. We also provide rich contextual and side information including interactions characteristics (such as temporal information, watch duration and watch percentage), user demographics and rich movies meta-information. In addition, we describe the MTS Kion Challenge - an online recommender systems challenge that was based on this dataset - and provide an overview of the best performing solutions of the winners. We keep the competition sandbox open, so the researchers are welcome to try their own recommendation algorithms and measure the quality on the private part of the dataset.