A recommender system for heterogeneous and time sensitive environment

Abstract

The digital game industry has recently adopted recommender systems to deliver the most relevant content and suggest the most suitable activities to players. Because of diverse game designs and dynamic experiences, recommender systems typically operate in highly heterogeneous and time-sensitive environments. In this paper, we describe a recommender system at a digital game company which aims to provide recommendations for a large variety of use-cases while being easy to integrate and operate. The system leverages a unifed data platform, standardized context and tracking data pipelines, robust naive linear contextual multi-armed bandit algorithms, and experimentation platform for extensibility as well as fexibility. Several games and applications have successfully launched with the recommender system and have achieved signifcant improvements.