How to use SAS for detecting Medical Insurance Fraud?

[Allancubos]

Can someone let me know on how can I utilize SAS for Insurance Fraud Detection specifically in the line of Medical Insurance?

[sbxkoenk]

Hello @Allancubos ,

As you can imagine several books can be written on that topic!

I have many articles from journals, but articles are often in Dutch.

Have a look here:
1. Detecting health care claims fraud
How to get faster results, fewer false positives and more fruitful investigations

https://www.sas.com/en_be/insights/articles/risk-fraud/detect-health-care-claims-fraud.html

and here:

2. SAS® Detection and Investigation for Fraud in Healthcare
Prevent, detect and manage payment integrity issues from every angle.

https://www.sas.com/en_be/software/detection-investigation-for-health-care.html

When I did it, I was more focusing on unsupervised learning (like multivariate outlier and anomaly detection) rather than on supervised learning (as there's maybe a lack of historical cases confirmed as fraud and the non-detected fraud cases from the past are polluting your "good" part of the sample).

Feel free to post some more "focused" questions!

Good luck,

Koen

[sbxkoenk]

On top of my previous reply ... (see above) 

I see that you posted in Visual Analytics board.

Visual Analytics (VA) is a great tool for "consumption" of the output of your models, but for the models themselves you will need Visual Statistics (VS) and / or Visual Data Mining and Machine Learning (VDMML).

Visual Analytics can be used as a front-end for (a big part of) VS and VDMML but there are better front-ends for VS and VDMML.

Good luck,

Koen