Data-Driven Research on the Evaluation and Optimization of Table Tennis-Specific Teaching Effectiveness

Table tennis-specific teaching is often constrained by single assessment indicators, delayed feedback, and insufficient individualized guidance, making it difficult to understand students’ technical proficiency and training effectiveness accurately. This study develops a data-driven evaluation and optimization model based on multidimensional data collection. Wearable sensors, video analysis, and questionnaires are integrated to collect technical movement data, physiological indicators, and learning feedback from 120 table tennis students. The Analytic Hierarchy Process is used to determine weights for four evaluation dimensions: technical movement, physical fitness, tactical awareness, and theoretical knowledge. K-means clustering then classifies students into four levels—excellent, good, average, and needing improvement—and differentiated training programs are designed accordingly. After a 16-week optimized teaching intervention, serve accuracy in the experimental group increased from 68.3% to 85.7%, while the control group improved only from 68.5% to 74.2%. The model supports objective teaching diagnosis, personalized training, and realtime adjustment, and its sensing architecture is applicable to wireless data transmission and electromagneticcompatible sports monitoring systems.