Application of Data Mining Methods for Detecting Irregularities in Securities Market

Current procedure for monitoring securities market in Canada relies heavily on tips from outside and hard coded rules and thresholds. This approach leaves many suspicious cases out of investigation (i.e. false negatives). We introduce a data mining approach to identify irregularities in securities market. These irregularities are known as suspicious cases that might be associated with fraudulent activities and need to be investigated by auditors. Developing such methods requires a deep understanding of strategies that investment componies employ. During this internship, Koosha will work on building strategies for investments in securities market at FreeThink Capital, a hedge fund based in Edmonton. FreeThink Capital uses statistical analysis to understand the market and build investment strategies. Koosha will focus on time series analysis methods to detect patterns in securities market. This internship provides him an understanding of investoors’ approach and various investment strategies in securities market.

Faculty Supervisor:

Dr. Osmar Zaiane

Student:

Koosha Golmohammadi

Partner:

First Canadian Insurance

Discipline:

Computer science

Sector:

Finance, insurance and business

University:

University of Alberta