Events & News
Colloquium
| Category | Lecture |
| Date | Tuesday, October 28, 2008 |
| Time | 11:00 am |
| Location | GS 906 |
| Details | Refreshments will be served at 10:45PM in the 9th floor atrium |
| Speaker | Dr. Niall Adams |
| Affiliation | Dept of Mathematics, Imperial College, London |
Credit card transaction fraud detection
Fraud is a serious problem, impacting credit card providers, customers and vendors. I describe the character of the fraud detection problem in the context of credit card transaction processing in the UK. Various statistical and machine learning tools, both supervised and unsupervised, were deployed on suitably processed data. I show methods of combining these tools. Finally, it must be noted that credit card transaction data forms a data stream, that is, an unending sequence of non-stationary data. The standard data analysis approaches do not take this into account. I demonstrate how to modify certain methods to make them temporally adaptive.