Customer Segmentation Using Feature Set Generated from Customer Transaction Data

There is a high demand for automated fraud and money laundering detection and prevention systems since such activities costs millions to the financial industry every year. A key problem in detection techniques is the accurate and descriptive profiling of the accounts. Thus, it is important to identify the salient features in traction data that would enable us to accurately profile the accounts. Through accurate profiling of customer accounts the search for fraudulent activities can be narrowed down to high-risk group of accounts, which is much smaller than the total number of accounts which run up to the several million accounts. The project introduced under this proposal intends to develop the algorithms to identify a feature set from the account data. First salient features of the transactions will be identified. Then the dimension of the feature space will be reduced. Further customers will be segmented into groups of similar behaviour using the identified features and the appropriate metric. Finally, discriminate analysis will be performed to ensure integrity and to predict new customer segments.

Faculty Supervisor:

Dr. George K.I. Mann

Student:

Farid Arvani

Partner:

Verafin Inc.

Discipline:

Engineering

Sector:

Information and communications technologies

University:

Memorial University of Newfoundland