Smart badminton coaching: Development machine learning-based training system for basic badminton technique

Universitas Singaperbangsa Karawang, Indonesia

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Badminton is one of the most popular sports in Indonesia, yet the training of its fundamental techniques has traditionally relied on conventional and subjective methods. To address this limitation, we developed the Shuttle Smart Training Model, a machine learning-based system that integrates an AI-powered shuttle launcher (Shuttle Smart Machine) and a validated measurement tool (Shuttle Smart Test). The system was designed to improve the forehand and backhand clear techniques among athletes aged 15–17 years. Data collection involved expert validation, small and large group trials, and effectiveness testing with experimental and control groups. Results showed that the experimental group significantly improved their performance (post-test mean = 75.21; N- Gain = 56%) compared to the control group (post-test mean = 57.84; N-Gain = 20%). Statistical analysis (t = 13.087, p < 0.001) confirmed the model’s effectiveness. This research demonstrates the novelty of integrating structured drill-based training, AI-assisted devices, and objective testing instruments into a comprehensive badminton training system. The findings highlight the potential of technology-assisted sports coaching to enhance skill acquisition and provide a scalable solution for grassroots development.