Predicting Events in MOBA Games: Prediction, Attribution, and Evaluation

TL;DR

This paper introduces a large-scale dataset for MOBA game prediction, proposes interpretable event prediction methods using attribution techniques, and evaluates their accuracy and explanatory power.

Contribution

It provides a rich dataset, applies gradient-based attribution for interpretability, and introduces a fidelity metric for evaluating explanations in MOBA event prediction.

Findings

Gradient-based attribution improves interpretability.

Proposed fidelity metric effectively assesses explanation quality.

Competitive models achieve high prediction accuracy.

Abstract

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.