Neural data mining for credit card fraud detection
The prevention of credit card fraud is an important application for prediction techniques. One major obstacle for using neural network training techniques is the high necessary diagnostic quality: Since only one financial transaction of a thousand is invalid no prediction success less than 99.9% is acceptable. Due to these credit card transaction proportions complete new concepts had to be developed and tested on real credit card data. This paper shows how advanced data mining techniques and neural network algorithm can be combined successfully to obtain a high fraud coverage combined with a low false alarm rate.
| Author: | Rüdiger W. Brause, Timm Sebastian Langsdorf, Hans-Michael Hepp |
|---|---|
| URN: | urn:nbn:de:hebis:30-79161 |
| Document Type: | Article |
| Language: | English |
| Date of Publication (online): | 08.09.2010 |
| Year of first Publication: | 1999 |
| Publishing Institution: | Univ.-Bibliothek Frankfurt am Main |
| Source: | IEEE Int. Conf. on Tools with Art. Intell. ICTAI-99, IEEE Press, 1999, pp. 103-106 |
| HeBIS PPN: | 227736397 |
| Institutes: | Informatik |
| Dewey Decimal Classification: | 004 Datenverarbeitung; Informatik |
| Sammlungen: | Universitätspublikationen |
| Licence (German): |  Veröffentlichungsvertrag für Publikationen ohne Print on Demand |
