Predicting Events in MOBA Games: Prediction, Attribution, and Evaluation
This work provides a new dataset and interpretable prediction methods for MOBA game analysis, which is an incremental improvement for game developers and researchers.
This paper addresses the limitations of existing MOBA game prediction models by collecting and releasing a large-scale dataset with rich in-game features for Honor of Kings. They propose an interpretable method to predict four types of important in-game events, attributing predictions to input features using Integrated Gradients and SmoothGrad.
The multiplayer online battle arena (MOBA) games have become increasingly popular in recent years. Consequently, many efforts have been devoted to providing pre-game or in-game predictions for them. However, these works are limited in the following two aspects: 1) the lack of sufficient in-game features; 2) the absence of interpretability in the prediction results. These two limitations greatly restrict the practical performance and industrial application of the current works. In this work, we collect and release a large-scale dataset containing rich in-game features for the popular MOBA game Honor of Kings. We then propose to predict four types of important events in an interpretable way by attributing the predictions to the input features using two gradient-based attribution methods: Integrated Gradients and SmoothGrad. To evaluate the explanatory power of different models and attribution methods, a fidelity-based evaluation metric is further proposed. Finally, we evaluate the accuracy and Fidelity of several competitive methods on the collected dataset to assess how well machines predict events in MOBA games.