Every Crime Has a Footprint. The Challenge Is Finding It

At U of T, students aren’t just studying artificial intelligence – they’re using it to track global crime.

Each year, hundreds of students analyze financial transaction data to detect criminal activity in a competition organized by UTM’s Institute for Management and Innovation.

Past iterations of the IMI Big Data and Artificial Intelligence competition have asked students to identify bad actors engaged in human trafficking, the illegal wildlife trade and fentanyl production. This year’s focus: detecting indications of complex crimes such as terrorist financing.

“Every crime has a footprint,” says Kevin Yousie, chair of the competition’s organizing committee and an associate professor at UTM. “Many criminal organizations are global in scope with multiple divisions. If you follow their transactions, you begin to see who they’re connected to and what might be happening elsewhere in the world.”

The data – synthesized information that models real financial data from event partner Scotiabank – includes tens of millions of rows of transactions. Over four months, teams use advanced analytics, machine learning and generative AI tools to identify suspicious patterns.

This year, 430 students – from undergraduate to PhD across U of T’s three campuses – formed 90 teams that competed over several rounds. Scotiabank provided mentorship from its own data scientists and a large portion of the competition’s $30,000 in prize money. Winners were to be announced in April.

Beyond the cash reward, participants say the real value of the exercise is experiential learning that mirrors the challenges faced by financial institutions and law enforcement agencies worldwide.

Thomas Lee, a fourth-year computer science student who enjoyed the contest enough to come back for a second year, says: “It’s compelling to compete against some of the best minds at the University of Toronto to tackle real-world problems.”