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
Rene Perez, financial crimes consultant, Jack Henry & Associates

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: Safeguarding Election Integrity in the Digital Age

“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.

About the Author

Suparna Goswami

Suparna Goswami

Associate Editor, ISMG

Goswami has more than 10 years of experience in the field of journalism. She has covered a variety of beats including global macro economy, fintech, startups and other business trends. Before joining ISMG, she contributed for Forbes Asia, where she wrote about the Indian startup ecosystem. She has also worked with UK-based International Finance Magazine and leading Indian newspapers, such as DNA and Times of India.

Around the Network

Our website uses cookies. Cookies enable us to provide the best experience possible and help us understand how visitors use our website. By browsing, you agree to our use of cookies.