Subscribe to DSC Newsletter

I'm going to work on a credit card fraud project. I heard one of methods is to build profile for each card holder and when new transaction comes in, compare it with profile to see whether it is abnormal.

Does anyone have any experience/knowledge on this? How to build the profile and what algorithms or technique to determine abnormality? Thanks.


Views: 551

Reply to This

Replies to This Discussion

Hi Jason,

I may be of some help for you as a fraud analyst.

You may contact me by email [email protected] and I am eager to help and advise. 


On Data Science Central

© 2021   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service