Innovative Credit Card Fraud Detection System

(Università della Svizzera italiana, May 03, 2021)

A team of researchers at the Università della Svizzera italiana led by Dr. Bruno Buonaguidi and Professor Antonietta Mira, in collaboration with a major credit card company in Switzerland, recently developed an innovative probabilistic model for the efficient detection of fraudulent transactions. As explained by Dr. Buonaguidi, the algorithm first studies the behavior of credit card users to understand their purchasing habits, as well as the characteristics of transactions that are know to be fraudulent, in order to return, for each credit card user, a personalized threshold that will be used to declare the nature of the transactions. In the second step, the algorithm then calculates the probability that a subsequent transaction of a credit card user is fraudulent, and when this probability exceeds the threshold referred to in the previous point, the fraud alarm is raised.