Detection of unusual transactions - ON-103
Preferred Disciplines: Machine Learning (PhD or Post-Doc)
Project Length: 4-6 months (1 unit)
Desired start date: As soon as possible
Location: Toronto, ON
No. of Positions: 1
Preferences: University of Toronto, Universite de Montreal, University of Waterloo.
About the Company:
The partner is a financial institution with a large client base in both retail and commercial banking.
The ability of financial institutions to detect unusual transactions involving their clients is important for risk management, customer retention and business development purposes. The detection of unusual transaction is a complex problem that depends on the transactional network, the nature of the clients’ financial activities, and the domain of application. In this project, the researcher will develop a framework for the detection of unusual transactions.
- Survey literature on anomaly and fraud detection
- Build and test a framework for anomaly detection in the client transactional network
- Deep learning
- Reinforcement learning
Expertise and Skills Needed:
- Deep knowledge of machine learning and reinforcement learning
- Programming in R or Python. Knowledge of TensorFlow is a plus.
For more info or to apply to this applied research position, please