ContentWise Impressions: An Industrial Dataset with Impressions Included

Abstract

In this article, we introduce the ContentWise Impressions dataset, a collection of implicit interactions and impressions of movies and TV series from an Over-The-Top media service, which delivers its media contents over the Internet. The dataset is distinguished from other already available multimedia recommendation datasets by the availability of impressions, i.e., the recommendations shown to the user, its size, and by being open-source. We describe the data collection process, the preprocessing applied, its characteristics, and statistics when compared to other commonly used datasets. We also highlight several possible use cases and research questions that can benefit from the availability of user impressions in an open-source dataset. Furthermore, we release software tools to load and split the data, as well as examples of how to use both user interactions and impressions in several common recommendation algorithms.

8 pages, 2 figures

References in corpus (3)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• Artist-driven layering and user's behaviour impact on recommendations in a playlist continuation scenario

Cited by in corpus (7)

• Take a Fresh Look at Recommender Systems from an Evaluation Standpoint
• A Methodology for the Offline Evaluation of Recommender Systems in a User Interface with Multiple Carousels
• Deep Evolutional Instant Interest Network for CTR Prediction in Trigger-Induced Recommendation
• Measuring the User Satisfaction in a Recommendation Interface with Multiple Carousels
• Neural Click Models for Recommender Systems
• Impression-Aware Recommender Systems
• On the Reliability of Sampling Strategies in Offline Recommender Evaluation