Predicting Outcomes in Video Games with Long Short Term Memory Networks
This work addresses audience engagement in video game tournaments, but it is incremental as it applies an existing method to a new domain with limited data.
The paper tackled the problem of predicting winners in E-sports tournaments in real-time to enhance audience engagement, using an LSTM network based on player health indicators and achieving competitive performance against Transformer models in the game Super Street Fighter II Turbo.
Forecasting winners in E-sports with real-time analytics has the potential to further engage audiences watching major tournament events. However, making such real-time predictions is challenging due to unpredictable variables within the game involving diverse player strategies and decision-making. Our work attempts to enhance audience engagement within video game tournaments by introducing a real-time method of predicting wins. Our Long Short Term Memory Network (LSTMs) based approach enables efficient predictions of win-lose outcomes by only using the health indicator of each player as a time series. As a proof of concept, we evaluate our model's performance within a classic, two-player arcade game, Super Street Fighter II Turbo. We also benchmark our method against state of the art methods for time series forecasting; i.e. Transformer models found in large language models (LLMs). Finally, we open-source our data set and code in hopes of furthering work in predictive analysis for arcade games.