| |
 |
|
|
Science Forum Index » Space - Consult Forum » Credit Card Fraud Detection
Page 1 of 1
|
| Author |
Message |
| Piyush |
 Posted: Sat Nov 25, 2006 10:15 am |
|
|
|
Guest
|
Hi all,
I am looking to work on a credit card fraud detection model (using
SAS). The approach will be to develop business rules which when applied
to every transaction, will give some sort of a risk score, which can be
used to identify the likelihood of the transaction being good or bad.
If anybody has any study material/pointers/knowledge on credit card
fraud detection (or fraud detection in general), your help will be
highly appreciated.
Also, I already tried to develop one such model with some credit card
transaction datasets that I had access to. However, the problem was
that because they werent meant to be used for fraud detection, the data
sets did not have a labelled fraud field, ie, one which says whether
the transaction was good or bad. For me, without that field it was
impossible to build a meaningful model. Can anybody think of a
workaround - like generating a dummy fraud field for example? Maybe I
didnt have enough knowledge about building such systems. Your inputs
will be really helpful.
Thanks,
Piyush.
PS: Apologies for cross posting. |
|
|
| Back to top |
|
| cu8sfan |
| Posted: Mon Nov 27, 2006 10:58 am |
|
|
|
Guest
|
Piyush, I'm working on the exact same thing. You can contact me via
e-Mail. Basically you need an expert to tell you whether a transaction
is fraudulent or not. There's no way around this.
When building a model be careful to choose a model that can detect rare
events (let's hope fraud actually is a 'rare event' at your company (-:
). Otherwise, if you use a tree for instance you'll end up with one
branch that classifies all your transaction as non-fraud. This
classification will be right for most of the cases.
Piyush schrieb:
Quote: Hi all,
I am looking to work on a credit card fraud detection model (using
SAS). The approach will be to develop business rules which when applied
to every transaction, will give some sort of a risk score, which can be
used to identify the likelihood of the transaction being good or bad.
If anybody has any study material/pointers/knowledge on credit card
fraud detection (or fraud detection in general), your help will be
highly appreciated.
Also, I already tried to develop one such model with some credit card
transaction datasets that I had access to. However, the problem was
that because they werent meant to be used for fraud detection, the data
sets did not have a labelled fraud field, ie, one which says whether
the transaction was good or bad. For me, without that field it was
impossible to build a meaningful model. Can anybody think of a
workaround - like generating a dummy fraud field for example? Maybe I
didnt have enough knowledge about building such systems. Your inputs
will be really helpful.
Thanks,
Piyush.
PS: Apologies for cross posting. |
|
|
| Back to top |
|
| |
|
Page 1 of 1
All times are GMT - 5 Hours
The time now is Thu Nov 20, 2008 11:08 pm
|
|