Title:
CONSISTENCY MODELING OF HEALTHCARE CLAIMS TO DETECT FRAUD AND ABUSE
Document Type and Number:
WIPO Patent Application WO2003071388
Kind Code:
A3
Abstract:
Transaction-based behavioral profiling whereby the entity (102, 104) to be profiled is represented by a stream of transactions (106), is required in a variety of data mining and predictive modeling. An approach is described for assessing inconsistency in the activity of an entity (108), as a way of detecting fraud and abuse, using service-code information available on each transaction. Inconsistency is based on the concept that certain service-codes naturally co-occur more than do others. An assessment is made of activity consistency looking at the overall activity of an individual entity, as well as looking at the interaction of entities. Several approaches for measuring consistency are provided, including one inspired by latent semantic analysis as used in text analysis. While the description is in the context of fraud detection in healthcare, the techniques are relevant to application in other industries and for purposes other than fraud detection.
Inventors:
PATHRIA ANU K
ALLMON ANDREA L
DE TRAVERSAY JEAN
IANAKIEV KRASSIMIR G
SURESH NALLAN C
TYLER MICHAEL K
ALLMON ANDREA L
DE TRAVERSAY JEAN
IANAKIEV KRASSIMIR G
SURESH NALLAN C
TYLER MICHAEL K
Application Number:
PCT/US2003/004615
Publication Date:
December 18, 2003
Filing Date:
February 13, 2003
Export Citation:
Assignee:
FAIR ISAAC CORP (US)
International Classes:
G06Q10/10; G06Q20/40; G06Q40/00; G07F7/08; G16H10/60; G16H50/70; (IPC1-7): G06F17/60
Foreign References:
| US5819226A | 1998-10-06 | |||
| US6253186B1 | 2001-06-26 | |||
| US5359509A | 1994-10-25 | |||
| US6330546B1 | 2001-12-11 |
Download PDF: