Optimization of Sports Applied Curriculum System based on Association Rule Data Mining Algorithm

Optimized sports-applied curriculum system leveraging Association Rule Data Mining (ARDM) algorithms to enhance pedagogical effectiveness and student performance. By analysing large-scale student engagement datasets—including skill proficiency, training duration, and performance metrics—the system identifies hidden patterns and correlations through the Apriori algorithm and FP-Growth techniques. The framework dynamically tailors training modules by prioritizing high-impact exercises while minimizing redundant activities, achieving a 15.3% improvement in skill retention compared to conventional methods. Key evaluation metrics, including support (96.8%), confidence (97.5%), and lift (4.2), validate the algorithm’s precision in extracting actionable insights. Unlike traditional approaches, this system integrates real-time feedback adaptation, ensuring personalized training regimens that align with individual athlete progression. Experimental results demonstrate superior efficiency over rule-based (7.2% gain) and heuristic models (9.8% gain), particularly in team sports and endurance training. The proposed system bridges the gap between data-driven decision-making and sports pedagogy, offering a scalable solution for academic institutions and professional training centres. Beyond optimization, this work redefines curriculum design—transforming raw data into strategic training intelligence through associative learning.