Seminar: Financial fraud detection using machine learning

Md Kamrul Hasan
M.Sc. Candidate
Supervisor: Dr. Ting Hu

Financial fraud detection using machine learning

Department of Computer Science
Thursday, April 4, 2019, 12:00 p.m., Room EN 2022


Abstarct

Financial fraud is one of the most ethical issues in today's commercial sector. The main aims of the project are, to identify the credit card fraud from a large data set which has been taken from European Union credit card and to demonstrate, compare and analyze two machine learning algorithms and their findings in financial fraud detection. This project studies two commonly used machine learning anomalies detection algorithms, namely isolation forest and local outlier factors, in the financial fraud industry. It highlights key statistics and figures in the financial fraud detection sectors. Depending on the type of fraud faced by banks or credit card companies, this project will give various pros and cons of these two machine learning algorithms. Moreover, the prediction model trained in this project may have beneficial attributes in terms of cost savings and time efficiency, in order to minimize the financial fraud in the business world.

Contact

Department of Computer Science

230 Elizabeth Ave, St. John's, NL, CANADA, A1B 3X9

Postal Address: P.O. Box 4200, St. John's, NL, CANADA, A1C 5S7

Tel: (709) 864-8000