Fraud-Centric Merchant Embeddings - BC-887
Project type: ResearchDesired discipline(s): Engineering - other, Engineering, Computer science, Mathematical Sciences, Mathematics
Company: Mastercard AI Garage
Project Length: 6 months to 1 year
Preferred start date: 04/01/2024
Language requirement: English
Location(s): BC, Canada
No. of positions: 1
Desired education level: CollegeUndergraduate/BachelorMaster'sPhDPostdoctoral fellowRecent graduate
Open to applicants registered at an institution outside of Canada: Yes
About the company:
We work to connect and power an inclusive, digital economy that benefits everyone, everywhere by making transactions safe, simple, smart and accessible. Using secure data and networks, partnerships and passion, our innovations and solutions help individuals, financial institutions, governments and businesses realize their greatest potential. Our decency quotient, or DQ, drives our culture and everything we do inside and outside of our company. We cultivate a culture of inclusion for all employees that respects their individual strengths, views, and experiences. We believe that our differences enable us to be a better team – one that makes better decisions, drives innovation and delivers better business results. At AI Garage, we use state-of-the-art AI techniques to solve some of the most important problems in the financial world.
Describe the project.:
At Mastercard we work with improving and securing payments of millions of cardholders and merchants. One of the primary objectives of our 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, then follow up with advanced modelling techniques like Deep Metric Learning to create an embedding space specific to every kind of fraud. We will leverage graphs to create this embedding space, either by adding more features from a graph represented by merchants and cards, or by populating a graph after the embedding space is learnt, in which case this final graph will provide a lot of answers to questions regarding the respective fraud. On a more technical side this project will be at the intersection of graphs and Deep Metric learning and we would like to propose a new paradigm of machine learning combining these two powerful techniques which have been proven to provide benchmark results in a lot of real world applications.
Required expertise/skills:
Python, Pytorch, TigerGraph, Familiarity with Graph Neural Networks and Deep Metric Learning (Contrastive, Triplet Loss etc)
