Back To Projects
Predicting Running Injuries with Machine Learning Models
Elgin V. | Summer 2022 |

Is it possible to predict running injuries with only a dataset and machine learning models? This paper explores this question by using classification models, including the Logistic Regression model and the Random Forest Classifier model.


Is it possible to predict running injuries with only a dataset and machine learning models? This paper explores this question by using classification models, including the Logistic Regression model and the Random Forest Classifier model. In the dataset used, ten features were taken into account when predicting running injuries. With slight modifications, the Weighted Logistic Regression and over and down-sampling Random Forest Classifier models were used to mitigate the imbalance in the dataset. The results suggested that the best model was Weighted Logistic Regression and that the best score metric to take into account was the F beta score.

Explore More!

Published Paper
Elgin V.
Joseph Vincent
Aerospace Engineering PhD Candidate at Stanford

Related Projects

Application of AI to Tennis Match Footage Transcription

One of the best ways for tennis players to improve their game is to record and watch their own match footage, find patterns in the points they win and lose, and practice based on these realizations. However, watching match footage and documenting each point shot by shot is a very time-consuming process. This paper investigates an AI approach to transcribing tennis match footage, combining a deep convolution neural network (YOLOv4), a pose estimation model (Movenet), and a long short- term memory (LSTM) deep neural network. Looking at a transcript of each point will be far more efficient than watching entire match footage for a player to understand how they are losing and winning and analyze patterns in their game. The LSTM model in this project achieved accura- cies of 73.33% and 79.31% when classifying shot type (forehand, forehand volley, forehand slice, backhand, backhand volley, backhand slice, over- head/smash, and serve) for players on the close side and opposite side of the net, respectively, and 55.17% and 60.00% when classifying the di- rection of a shot (cross-court, down the line, down the middle, inside in, inside out, out wide, down the t, and body) for players on the close side and opposite side of the net, respectively.
Marco Y. | Summer 2022
Mentored by Eric Bradford
Revolutionizing Football: Using Machine Learning to Predict Future Performances for Quarterbacks

It is important to have a reliable application that can aid users of betting and fantasy football in which players they should put bet on, or choose for their fantasy teams. My motivation behind this project was to create something that could further betting and fantasy football, and even increase traction.
Anya N. | Winter 2023
Mentored by Eric Bradford
Comparison of Machine Learning Models to Best Predict Game Attendance in Major League Baseball

To forecast Major League Baseball game attendance, this study employs six different regression models commonly used for machine learning.
Seohyun P. | Fall 2023
Mentored by Kasra Koushan