Project Info:

I developed an injury risk prediction system for sports, leveraging AWS for scalable data processing and model deployment. I enriched historical player data with performance metrics, injury history, and more, implementing Random Forest, Gradient Boosting, and Deep Learning models for accurate predictions. The project showcases my expertise in ML, Data Engineering, and cloud computing, making it a valuable addition to my portfolio. The models enable real-time risk assessments, enhancing insights in the world of sports injury prevention.

Result Obtained :

Our model achieved strong performance metrics with an accuracy of 85%, precision of 80%, and recall of 90%. It uncovered crucial insights, linking elevated acute-to-chronic workload ratios and insufficient recovery periods to increased injury risks. Deployment on AWS ensures scalability and real-time access for effective sports injury risk management.

Project Details:

• Technologies:AWS, Python, Scikit-learn, Matplotlib, Docker, Kubernetes, MLflow, Tableau