Detection of unusual transactions - ON-103
Preferred Disciplines: Machine Learning - PhD candidates and postdoctoral fellows
Project Length: 4 to 6 months
Desired start date: January 8, 2018
Location: Toronto, ON
No. of Positions: 1
Preferences: University of Toronto, Universite de Montreal, University of Waterloo. Language: English.
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
Check your eligibility and find more information about open projects.
Complete this webform. You will be asked to upload your CV. Remember to indicate the title of the project(s) you are interested in and obtain your professor’s approval to proceed!
Interested students need to get the approval from their supervisor and send their CV along with a link to their supervisor’s university webpage by applying through the webform or directly to Fiona Cunningham at, fcunningham(a)mitacs.ca.