BookmarkSubscribeRSS Feed
Babloo
Rhodochrosite | Level 12

I need to do detect a fraud using SAS EMiner. Appreciate if someone tell me the stuffs to look in output after running the fraud program.

 

I would be thanksful if someone give me the skeleton to conduct a fraud analysis in SAS EMiner.

 

Thank you!

4 REPLIES 4
Reeza
Super User

It doesn't work like that. It can be very subject specific. 

Fraud can be 0/1 but then you could do a second stage model to account for,the amount. The variables that go in the model can vary significantly based on subject area and the type of variables will impact the type of analysis possible. 

 

If you haven't already I would suggest working through the following guide:

 

http://www.sas.com/store/books/categories/usage-and-reference/predictive-modeling-with-sas-enterpris...

Babloo
Rhodochrosite | Level 12

Thanks for the insights. Appreciate if you write me the very short answer for my question. Because it would stay in memory for long time when compared to bookish languague. 

 

Tutorial which you mentioned seems to be a paid material. Could you please direct me to the some free tutorial?

 

Thank you!

Reeza
Super User

Look for false positive rate and model accuracy primarily including type 1 & 2 errors. 

 

When I started learning EM this was the best resource I could find. There aren't a lot of free resources for EM. 

That was a year ago. 

 

Good Luck. 

 

 

 

Babloo
Rhodochrosite | Level 12

Thank you for the reply and I hope I can remember your words for years. I believe false positive rate can be seen in confusion matrix. May I also know how/where to find the model accuracy?

sas-innovate-2024.png

Join us for SAS Innovate April 16-19 at the Aria in Las Vegas. Bring the team and save big with our group pricing for a limited time only.

Pre-conference courses and tutorials are filling up fast and are always a sellout. Register today to reserve your seat.

 

Register now!

How to choose a machine learning algorithm

Use this tutorial as a handy guide to weigh the pros and cons of these commonly used machine learning algorithms.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 4 replies
  • 907 views
  • 1 like
  • 2 in conversation