A causal discovery approach based on synthetic data and its application in contaminant transport modelling and card fraud detection

This project will apply causal discovery methods to two model-generated datasets. One is a dataset describing the transport of emerging contaminant metformin in the groundwater; the other is a card fraud transaction dataset. The method will examine the dataset’s underlying structure (data skeleton). Multiple new methods will be evaluated and tested on the datasets. The synthetic datasets are designed to reflect the real-world scenario to the maximum extent. The study results can help gain new knowledge on the contaminant transport process and the credit card fraud problem, test the performance of the causal recovery methods in different domains and guide the design of the causal discovery framework in multiple scenarios.

Faculty Supervisor:

Bing Chen

Student:

Partner:

NASDAQ Canada Inc

Discipline:

Engineering

Sector:

Information and Communications Technology; Health and Related Sciences & Technology; Finance and Insurance

University:

Memorial University of Newfoundland

Program: