MuLMINet: Multi-Layer Multi-Input Transformer Network with Weighted Loss

TL;DR

MuLMINet is a novel multi-layer multi-input transformer model designed to predict future badminton shots, demonstrating competitive performance in a major AI challenge and supporting further research with publicly available code.

Contribution

Introduces MuLMINET, a multi-layer multi-input transformer network for badminton shot prediction, advancing AI-based sports analysis methods.

Findings

Achieved 2nd place in IJCAI CoachAI Badminton Challenge 2023

Effectively predicts shot types and coordinates from match data

Provides publicly available code for research community

Abstract

The increasing use of artificial intelligence (AI) technology in turn-based sports, such as badminton, has sparked significant interest in evaluating strategies through the analysis of match video data. Predicting future shots based on past ones plays a vital role in coaching and strategic planning. In this study, we present a Multi-Layer Multi-Input Transformer Network (MuLMINet) that leverages professional badminton player match data to accurately predict future shot types and area coordinates. Our approach resulted in achieving the runner-up (2nd place) in the IJCAI CoachAI Badminton Challenge 2023, Track 2. To facilitate further research, we have made our code publicly accessible online, contributing to the broader research community's knowledge and advancements in the field of AI-assisted sports analysis.