AI-enabled Prediction of eSports Player Performance Using the Data from Heterogeneous Sensors
This work provides a performance monitoring and learning tool for professional and amateur eSports teams, addressing a gap in current eSports analytics.
This paper addresses the lack of analytical and training tools in eSports by developing an AI-enabled solution to predict player in-game performance using physiological, environmental, and game chair sensor data. The recurrent neural network model, enhanced with an attention mechanism, achieved a ROC AUC score of 0.73, and can predict performance even for players not included in the training set.
The emerging progress of eSports lacks the tools for ensuring high-quality analytics and training in Pro and amateur eSports teams. We report on an Artificial Intelligence (AI) enabled solution for predicting the eSports player in-game performance using exclusively the data from sensors. For this reason, we collected the physiological, environmental, and the game chair data from Pro and amateur players. The player performance is assessed from the game logs in a multiplayer game for each moment of time using a recurrent neural network. We have investigated that attention mechanism improves the generalization of the network and provides the straightforward feature importance as well. The best model achieves ROC AUC score 0.73. The prediction of the performance of particular player is realized although his data are not utilized in the training set. The proposed solution has a number of promising applications for Pro eSports teams and amateur players, such as a learning tool or a performance monitoring system.