There is minimal automation for proactively identifying and preventing fraud. Systems in place are largely rules-based systems that often return high numbers of false-positive alerts and are exploited by fraudsters as they learn the rules and how to circumvent them.
Goals and Objectives
Apply fraud management techniques that utilize anomaly detection, guest/passenger baseline scoring, and appropriate risk tolerances to identify and prevent fraudulent transactions.
AI, analytics, machine learning, and fraud detection software
Use Case Summary
Automated fraud management will identify potential sources of fraud and alert managers. Solutions will offer actions to take and will provide minimal false positives, maximizing revenue opportunity while minimizing fraud risk.