Artificial Intelligence & Machine Learning , Card Not Present Fraud , Fraud Management & Cybercrime
How Payment Card Fraud Detection Must Change
Insights on Refining AI Models to Adapt to Current Environment
Some payment card fraud detection systems that rely on artificial intelligence are now less effective because of changes in consumers’ habits during the COVID-19 pandemic, says Rene Perez of Jack Henry & Associates, a technology and payment processing services company (see: Using Artificial Intelligence to Fight Money Laundering).
See Also: The SIEM Selection Roadmap: Five Features That Define Next-Gen Cybersecurity
“Models are not able to adapt since they look at historical information. The history predicts the future. But people’s buying patterns have changed, making it difficult for companies to rely on old AI models,” Perez says.
In this video interview with Information Security Media Group, Perez discusses:
- Why card-not-present fraud has been on the rise;
- How to train the AI models to adapt to current circumstances, including the shift to ecommerce transactions;
- What types of payment fraud will dominate in the months to come.
Perez is a financial crimes consultant with Jack Henry & Associates who has about 20 years of experience. Prior to Jack Henry & Associates, Perez worked in fraud prevention at a top 60 bank in the U.S.
