Fair Isaac Corporation

Chris Erickson

Stuart L Crawford

Sergei Tolmanov

Michael Steele

Megan Thorsen

Navin Doshi

Kashyap Babu Rao Kolipaka

Gaurav Chhaparwal

Prasun Kumar

Victor Miagkikh

Fraud detection is facilitated by developing account cluster membership rules and converting them to database queries via an examination of clusters of linked accounts abstracted from the customer database. The cluster membership rules are based upon certain observed data patterns associated with potentially fraudulent activity. In one embodiment, account clusters are grouped around behavior patterns exhibited by imposters. The system then identifies those clusters exhibiting a high probability of fraud and builds cluster membership rules for identifying subsequent accounts that match those rules. The rules are designed to define the parameters of the identified clusters. When the rules are deployed in a transaction blocking system, when a rule pertaining to an identified fraudulent cluster is triggered, the transaction blocking system blocks the transaction with respect to new users who enter the website.

Systems and methods for fraud detection via interactive link analysis

A request to compare strategies is received. The first strategy can be graphically represented by a first set of linked nodes arranged in a first form of decision logic. The second strategy can be graphically represented by a second set of linked nodes arranged in a second form of decision logic. The first set of linked nodes can be converted to a first modified set of linked nodes arranged in a third form of decision logic. The second set of linked nodes can be converted to a second modified set of linked nodes arranged in the third form of decision logic. A color-coded visual representation of the first modified set of linked nodes and the second modified set of linked nodes can be provided to a user. Related apparatus, techniques, and articles are also described.

Color-coded visual comparison of decision logic

Data characterizing a plurality of related action graphs is received. Thereafter, the plurality of related action graphs are transformed into a logically equivalent structure so that rendering of the logically equivalent structure can be initiated. Related interfaces, apparatus, systems, techniques and articles are also described.

Construction of decision logic with graphs

Growing community of inventors

El Cerrito, CA, United States of America

Chris Erickson