Can Adaptive Analytics Boost Debit Card Fraud Detection?

As frequent readers know, I'm a strong advocate for using adaptive analytics in credit card fraud detection. Some may wonder: Could the same analytic technology also boos…

AdobeStock_202213129@2x.jpeg
Scott Zoldi by Scott Zoldi

Chief Analytics Officer

expand_less Back to top

 

As frequent readers know, I'm a strong advocate for using adaptive analytics in credit card fraud detection. Some may wonder: Could the same analytic technology also boost fraud protection for debit cards? The answer: Absolutely!

First, a quick primer on adaptive analytics. These models continually "adapt" traditional neural network fraud models in response to real-time fraud tactics, some of which may have not been present during model training. This ability to learn from in-production fraud trends helps financial institutions recognize newer schemes and consequently catch more fraud.

We recently tested the value of using adaptive analytics on a FICO debit consortium model, specifically our recently released FICO® Falcon® Fraud Manager UK-Ireland Debit 12.0 model. Adaptive analytics detects 6% more fraud accounts at a 10:1 account false positive ratio (AFPR). By keeping the detection rate fixed, adaptive analytics reduces the model’s false positive ratio by more than 10%, up to a 40% account detection rate (ADR), as shown in the graphic below.

Adaptive-Model_Blog-Graphic-2014-450px_n

Given these performance improvements, not to mention the value adaptive analytics already brings to our Falcon credit models, FICO is introducing adaptive analytics to our Falcon debit models. Adaptive models are available today for clients of UK-Ireland Debit 12.0, and will be available later this year for our International Debit and US Debit clients. After singing the praises of adaptive analytics for years on this blog, I’m pleased that more of our clients will be able to take advantage of the benefits that these models bring.

 

Scott Zoldi
Scott Zoldi
Dr. Scott Zoldi is chief analytics officer at FICO, responsible for artificial intelligence (AI) and analytic innovation across FICO's product and technology solutions. Dr. Zoldi is a named inventor on 150+ active patents and pending patent applications, with more than 100 granted. Scott is an industry leader in the responsible use of AI, Generative AI (GenAI), and Agentic AI, as well as an outspoken proponent of AI governance and regulation. His groundbreaking work in focused language models (FLMs) for GenAI and a patented use of blockchain technology for AI model development governance has helped propel Scott to AI visionary status. His recent awards include Constellation Research Award AI150, Tech Leadership Award from Banking Tech Awards, Tech Influencer Highly Commendable Award from DataIQ Data & AI Awards, San Diego Business Journal - Leaders of Influence in Technology (2025); Tech Leadership - Software & Services Provider from Fintech Futures, MachineCon AI100 Award, Innovator Award from American Banker (2024); Global Finance Innovator Award (FICO) (2023); and Corinium Future Thinking Award (2022). An enthusiastic member of the southern California tech community, Scott serves on the Boards of Directors of Software San Diego and the San Diego Cyber Center of Excellence. He received his Ph.D. degree in theoretical and computational physics from Duke University, and his work has been published in The Harvard Business Review and numerous scientific journals.

When not at his office or on a plane, Scott can often be found in his Ford Bronco, exploring the desert around San Diego with his family. To hear more of his views follow Scott on LinkedIn and BlueSky @ScottZoldi.
See all posts
chevron_left Blog home
RELATED POSTS

Popular Posts

Take the next step

Connect with FICO for answers to all your product and solution questions. Interested in becoming a business partner? Contact us to learn more. We look forward to hearing from you.

Contact us