Skip to main content
Image
Class of 2022
Major:
Mathematics
Statistics

Brenden Bready '22 is a mathematics and statistics major at St. Lawrence University. As an active club soccer player, he enjoys the idea of using math to identify patterns in sports, which inspired the idea for this project. He often plays on soccer turf himself, so he was very curious about the possibility of non-contact injury through movement. He hopes to continue using various analytics techniques to pursue further research about patterns in sports through the rest of his time at St. Lawrence.

Advisor
Description

Football professionals are always concerned about injury due to the high level of contact within the sport, but non-contact injuries are often overlooked. This summer, I attempted to investigate the relationship between non-contact injuries and their relation to the playing surface a player was injured on. The data was provided by the NFL on a site called Kaggle, which is where companies will put out their data for data scientists to analyze. The data was provided in three separate datasets, which would have to be combined to make a complete analysis. The first dataset provided 105 observations the injuries, the second contained 267,000 observations about each play, and the third contained over 76 million observations with second-by-second information about each play. Through the summer, I worked to organize and visualize the data to truly understand the breakdown of injuries by playing surface, and other predictor variables that could be linked to injury. Through the modeling, I was unable to find a way to predict injury from playing surface. The main reason for this is because an injury is such a rare event, and so trying to model 105 injuries in 267,000 plays is nearly impossible using normal modeling techniques. This resulted in the breaking down of the dataset by player, but these results because significantly less effective when trying to make predictions for certain situations. The project has left off with questions for future analyses about the best way to model rare event data.