Self-calibrating fraud detection

US8027439B2 · kind B2 · utility

Assignee

• Fair Isaac Corporation · US

Inventors

• Scott Michael Zoldi · San Diego, US
• Steven G. Wu · San Diego, US
• Fei Chen · Nanjing, CN

Key dates

• Filing date: Sep 18, 2006
• Grant date: Sep 27, 2011
• Expiry date: May 4, 2030

Classification

• Technology area (CPC G): Physics
• CPC primary: G06Q40/00
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

A method for dynamically updating a model is described. The method includes accessing a model that specifies expected characteristics for a transaction. The model includes variables associated with fraud. The method also includes receiving at least one value for each of the variables while monitoring transactions, and updating a distribution of values for each variable based on the received value. The received value is compared with the updated distribution to determine a deviation from a threshold value associated with a percentile of the updated distribution that is indicative of fraud.