injury-prediction

Sports performance telemetry analytics — EDA, KPI engineering & injury risk prediction

athlete-injury-risk-analyzer

Injury prediction model using machine learning to analyze factors like workload, player metrics, and environmental conditions. It identifies injury risk patterns early, enabling preventive actions, improved training decisions, and reduced injury occurrence in athletes.

Multi-class ML model to predict football injury types (ACL, Hamstring, Lower Back, Ankle) | AdaBoost best performer | AUC: 0.85 | Synthetic data via Gretel.ai

Predicting the probability of injury in cricket players based on recent match workload

ACL injury prediction with classical machine learning techniques (primarily addressing the extreme class imbalance).

Predicción de lesiones sin contacto a 7 días con datos sintéticos de carga (wearables): pipeline completo de ML con validación temporal, manejo del desbalance e interpretabilidad (SHAP).

Predicts the probability of an athlete getting injured based on physical and training parameters using a custom-built Gaussian Naive Bayes classifier with PCA, served via FastAPI and Streamlit.

This analysis uses insights gathered from reputable, research-backed, and publicly accessible football and sports-injury resources to predict potential injury risks, identify patterns, and recommend preventive strategies.

Hybrid deep learning model (TCN + BiGRU + Transformer) for predicting athlete injury risk from multi-sport time-series training load data. Full EDA, feature engineering, calibration, and evaluation dashboard included.

Comprehensive machine learning analysis on player injury prevention for the San Diego Padres baseball team (simulated dataset) conducted in MIS 401: Business Intelligence and Analytics at SDSU. Built in RapidMiner Studio (v10.2) using logistic regression, deep learning, and decision tree models.

ML-powered football injury risk prediction using wellness & workload data, Random Forest, XGBoost, and Streamlit deployment.

ML-powered athlete injury risk prediction · XGBoost · Gender-specific models · 750k rows · Live dashboard