The Path of the Righteous: Using Trace Data to Understand Fraud Decisions in Real Time

Abstract

Trace data—users’ digital records when interacting with technology—can reveal their cognitive dynamics when making decisions on websites in real time. Here, we present a trace-data method—analyzing movements captured via a computer mouse—to assess potential fraud when filling out an online form. In contrast to incumbent fraud-detection methods, which analyze information after submission, mouse-movements traces can capture the cognitive dynamics of a decision to be fraudulent as it is happening. We report two controlled studies using different tasks, where participants could freely commit fraud to benefit themselves financially while we captured mouse-cursor movement data. We found that participants who entered fraudulent responses moved their mouse significantly slower and with greater deviation. We show that the extent of fraud matters such that more extensive fraud increased movement deviation and decreased movement speed. These results demonstrate the efficacy of analyzing mouse-movement traces to detect fraud during online transactions in real time, enabling organizations to confront fraud proactively as it is happening at Internet scale.

Keywords: Trace Data, Mouse-Cursor Movements, Cognitive Dissonance, Bayesian Analysis