Abstract
The influence of the game streaming industry in video games is non-negligible. However, the work using both game streaming data and game active player data is limited. There are many challenges when it comes game related data, such as Twitch data is noisy, and not all the games’ popularity can be reflected by active player number. In this work, we set up a forecasting task to predict Steam active player numbers for a selected set of games. The study shows that with the extra information provided by Twitch data, we can forecast Steam active players slightly better in terms of MAPE. In addition, this quantitative study confirms the importance of the streaming industry to the gaming industry.
Original language | English |
---|---|
Title of host publication | Proceedings of ELM 2022 |
Subtitle of host publication | Theory, Algorithms and Applications |
Publisher | Springer |
Pages | 37-45 |
ISBN (Electronic) | 978-3-031-55056-0 |
ISBN (Print) | 978-3-031-55058-4, 978-3-031-55055-3 |
DOIs | |
Publication status | Published - 2024 |
MoE publication type | A4 Article in a conference publication |