Fraud-Centric Merchant Embeddings

Mastercard works with improving and securing payments of millions of cardholders and merchants. One of the primary objectives of Mastercard’s work is to detect and prevent fraudulent payments. There are several ways of committing such fraud, often such fraud can happen due to vulnerability of the merchant to such fraudulent threats and several other underlying factors. The first objective of this project is to get an understanding of what attributes are necessary for modelling this kind of a threat to our cardholders. Our second goal is to find an embedding space of the graph of transactions that preserves those attributes and can be used ny a simple classifier to efficiently determine whether a novel transaction is fraudulent or legitimate, with high accuracy.

Faculty Supervisor:

Michel Barbeau

Student:

Partner:

Mastercard

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

Carleton University

Program: