The performance optimization model of adjusting technical and tactical decisions with ideal usages for elite female table tennis players.

backgroundAnalyzing technical and tactical behaviors in table tennis and developing optimization strategies are essential for improving player performance. However, most existing studies focus on evaluating the effectiveness of individual behaviors, but offer limited insight into how these behaviors should be strategically used. This highlights the need for data-driven methods that guide practical usage decisions.

methodThis study proposes a model to support decision-making for elite female table tennis players using three indicators: Behavior Scoring Performance (BSP), Ideal Usage Rate (IUR), and Behavior Usage Adjustability (BUA). These indicators identify optimal behavior patterns and suggest adjustments to improve scoring. For each technical-tactical attribute (stroke technique, placement, position, and game action), the model fits a performance curve to characterize the BSP-IUR relationship and guide tactical refinement. The approach operates on two levels: macro (group-level across matches) and micro (match-specific optimization).

resultsAnalysis of 59 matches between Chinese and Japanese players yielded actionable recommendations, such as increasing Neutral play while reducing Defense against Neutral and Offense actions, refining Topspin and Block usage, and enhancing serve variety among Japanese players. The most effective adjustment of a single stroke technique behavior yielded an average scoring rate increase of 1.10%. When applying all IURs of stroke techniques in a match, the average improvement reached 6.4% (SD = 4.3%). The model also supported tailored decision-making when applied to individual matches, highlighting its utility for data-driven, match-specific performance optimization.

conclusionsThis study introduces a data-driven framework to address the practical gap in optimizing behavior usage in elite women's table tennis. By incorporating scoring performance, it identifies ideal usage patterns and informs effective adjustments. The framework outperforms baseline strategies and demonstrates robustness, supporting its value for tactical improvement.