Comparing Three Machine Learning Models That Predict an NFL Player’s Position Based on Height and Weight

This research paper uses machine learning algorithms to investigate the connection between football players' weight, height, and positional assignments in the National Football League (NFL).The paper compares three machine learning algorithms: K-Nearest Neighbors (KNN), Decision trees, and Random Forests.We further investigated the optimal parameters through hyperparameter tuning to compare our machine-learning models.We used performance metrics such as accuracy scores and raw confusion matrices to compare our models.Our results showed that KNN produced the highest accuracy.The findings shed light on the connection between NFL positional assignments and player physical characteristics.The findings can potentially improve team performance and success in the NFL by influencing player selection and development plans.