This data project was commissioned by Conor McQuiston, the director of football analytics for the USC Trojans, so his department has more room to test out gameplans and ideas for the Trojans. (Image /Dall-E)
Every football game generates thousands of pieces of data, from tackles and touchdowns to formations and penalties. Turning that information into insights, however, is a challenge. The USC Trojans have been one of the many college football teams using data to their advantage, but the amount of information they have access to could prove overwhelming.
To help them make better use of that data, a group of students and recently graduated alumni from the analytics master’s program within the Daniel J. Epstein Department of Industrial & Systems Engineering (ISE) at the USC Viterbi School of Engineering is building a database with play-level results from thousands of FBS games. The students are supervised by Bruce Wilcox, an associate professor of industrial and systems engineering practice at USC Viterbi.
Their goal is to organize years of college football data into a searchable data warehouse that will help the Trojans analyze trends, test ideas and prepare for opponents more efficiently.
This trove of data is being sorted into an easily accessible data archive, typically known as a “data warehouse.” This “warehouse” is sorted into “data marts,” which are more focused sections within the warehouse for specific areas of analysis.
This “warehouse” won’t just be collecting dust, though: The database will allow USC analysts to quickly test ideas, compare trends across seasons and opponents, and eventually study individual player performance as well as plays.
It will actively help the Trojans engage with years of football history to create more actionable analysis to prepare for their next game. The Viterbi team plans to later expand to breaking down individual players, not just the plays themselves. But for now, they are building a play-level data mart, with one row for each play of each game for the last 10 years.
“I’m just astounded at the amount of data that’s collected,” Wilcox said. “We hope, by the end of the summer, to have that first data warehouse operating.”
Building a Better Playbook
Wilcox assembled his team in the beginning of the spring semester, and he asked Saloni Deepak Prabhu — who graduated from the chemical engineering master’s program at the Mork Family Department of Chemical Engineering and Materials Science in May 2025 – to lead the day-to-day operations and the technical work on the project. Wilcox and Prabhu met when Prabhu elected to take data-focused coursework for her degree and took on his course, later joining his research team and the ISE department for these data engineering projects. Prabhu emphasized the importance of breaking down the complex data involved in a football game into a simple format, making game preparation far more efficient for the Trojans.
“We are building a data warehouse so the analysts can get direct access to well-modeled structured data, so that they can spend time on their analysis and the time spent on preparing the data is eliminated altogether,” Prabhu said.
This data project was commissioned by Conor McQuiston, the director of football analytics for the USC Trojans. McQuiston explained that organizing this data will give his department more room to test out ideas for the Trojans to understand what might or might not work on game day.
“So many different teams have tried so many different things that just having access to all this data lets us run natural experiments,” McQuiston said. “What has and hasn’t worked, and what can we learn from that?”
The Viterbi team was up to the challenge of making sure those experiments can run smoothly for the team. Ironically, Prabhu’s student team had practically no experience with football itself.
From Data to Down-and-Distance
“American football was very new to me,” Prabhu said. “Before joining this project, I researched about how American football works, got to know its rules and some technical stuff, and Conor was a great help also.”
For his part, McQuiston was impressed by how quickly the Viterbi team began to understand how American football functions.
“Many of the students in this program are international students, and while American football is gaining popularity internationally, it’s still not a sport most of them grew up watching,” McQuiston said. “The speed at which the international students were able to learn a sport as complex as American football was really impressive.”
Prabhu and her team’s lack of knowledge in this field didn’t impact their methodology, as they felt their work was no different from any other data-centric task in one key way. In short: context matters.
“We don’t build in isolation,” Prabhu said. “We need to understand the requirements of the ‘business,’ which in this case is football. It is very important for us to understand what all requirements are and what areas of analysis they want.”
Football may not be a sport these students knew much about before, but that didn’t stop the Viterbi students from helping out their team by building this contextualized, carefully compiled data. They’re starting to enjoy the game, too.
“I am actually a football fan now,” Prabhu said. “I’m learning step by step, but yeah, I am.”
Published on August 5th, 2026
Last updated on August 5th, 2026