- In the five years since its launch, financial institutions around the world have adopted the Federal Reserve’s FraudClassifier model
- One international adopter of the model is Payments NZ, which governs New Zealand’s three core payment clearing systems
- Organizations report that they use the FraudClassifier model to enhance internal reporting, support data-driven fraud mitigation strategies, and improve coordination across the payments industry
- The FraudClassifier model integrates with the ScamClassifier℠ model to further enhance scam mitigation efforts
In the five years since its introduction, the Federal Reserve’s FraudClassifier model (Off-site) has achieved growing global adoption among financial institutions, fintechs and payment service providers, and can offer greater value through integration with the ScamClassifier model (Off-site), introduced in 2024. Underscoring the FraudClassifier model’s international relevance, it recently was adopted by Payments NZ (Off-site), which governs Aotearoa New Zealand’s three core payment clearing systems.
The FraudClassifier model has been quite the revelation from a reporting point of view, was more straightforward to implement than we expected, and is so easy to follow as a framework. Its structure has helped our members streamline industry fraud reporting and align with international best practices.
Chief Strategy and Innovation Officer
Payments NZ
How the FraudClassifier model helps mitigate fraud
The FraudClassifier model was designed to more consistently classify and help address fraud threats in a rapidly evolving payments landscape. The model uses a decision-tree approach with questions, supporting key terms and definitions to categorize fraud based on the method of execution and whether the transaction was authorized by the account holder.
This classification structure creates a consistent way to analyze and report fraud incidents for all payment types, which helps organizations better understand trends and strengthen prevention strategies. Organizations report that they use the FraudClassifier model to enhance internal reporting, support data-driven fraud mitigation strategies and improve coordination across the payments industry.
In just five years, the FraudClassifier model has gone from a promising framework to a widely adopted industry model — gaining momentum as financial institutions recognize the power of speaking the same fraud language. The model doesn’t just classify fraud — it clarifies it. That clarity empowers faster decisions, sharper investigations and better outcomes.
Financial Crimes Consultant and National Director of Financial Crimes Sales
Jack Henry™
Using the FraudClassifier and ScamClassifier models together to further strengthen fraud response
As fraud and scam tactics continue to evolve, interoperability between classification frameworks is essential. The FraudClassifier model aligns with the ScamClassifier model, a complementary framework developed to address socially engineered scams, including authorized push payment (APP) fraud and impersonation attacks. The models’ structures allow them to be used together or independently (Off-site), so organizations can classify fraud and scams with consistency and precision.
These models support a holistic approach to fraud and scam classification across the payments industry. With the continued rise in digital payment volume and increasing sophistication of fraud and scam tactics, it has never been more critical to have consistent, integrated classification tools that are simple and easy to use.
As it enters its sixth year, the FraudClassifier model’s expanding adoption — and its strategic alignment with complementary frameworks, such as the ScamClassifier model — represent progress toward building a more fraud-aware, resilient and globally connected payments ecosystem.
Sharing and use of the FraudClassifier and ScamClassifier models throughout the industry is encouraged; any adoption of these models is voluntary at the discretion of each individual entity. The FraudClassifier and ScamClassifier models are not intended to result in mandates or regulations, and do not give any legal status, rights or responsibilities, nor are the models intended to define or imply liabilities for fraud loss or create legal definitions, regulatory or reporting requirements. Absent written consent, the FraudClassifier or ScamClassifier models may not be used in a manner that suggests the Federal Reserve endorses a third-party product or service.
“CAMS (Certified Anti-Money Laundering Specialist)” is a registered trademark of ACAMS. “Jack Henry” is a registered trademark of Jack Henry & Associates, Inc.
