By Tim Boike, Vice President, Federal Reserve Bank of Chicago
Last June, the Federal Reserve announced the FraudClassifierSM model, which enables organizations to classify fraud, create a holistic view of fraudulent events and help them manage fraud more strategically.
Since then, we have held numerous virtual discussions with payments and fraud professionals about the model, how it works, its value propositions and why they should consider adoption. Here is a snapshot of what we have been hearing from our industry colleagues:
- “This model is great!” Industry stakeholders in our engagements commended the model for being both comprehensive and intuitive in its application. As one early adopter stated, “The beauty of the FraudClassifier model is that it is both easy to use and provides valuable fraud information, regardless of the size of your institution.”
- There’s true value to the model. For many stakeholders, the fundamental value of the model is the ability to use it to consistently classify fraud within their organizations – which in turn, can help them better identify and react more quickly to fraud trends. More specifically, some said insights generated by using the model could help adjust their current preventive fraud analytics to reduce the risk of loss exposure while also protecting customers’ accounts.
- Small and mid-size financial institutions are beginning to use the model. Some organizations have shared that the model has helped them classify fraud types that they previously did not track, such as authorized party fraud. These organizations have found the model implementation was simple, employees are using the model consistently, and they are gaining valuable insights through its classifications – read about one organization’s experience.
- Large banks are enthusiastic. We also have had a positive response from a number of large financial institutions and the associations that represent them. We remain engaged with financial institutions of all sizes, while industry associations have been helpful partners by hosting presentations for their members about the model.
- Technology providers see opportunities. Notable leaders in fraud analytics, case management systems and core platform providers told us they have already incorporated, or plan to incorporate, the model into their product roadmaps.
- Research opportunities. Organizations that publish research on fraud are advancing their efforts to incorporate the model’s methodology into their own initiatives. Some noted this may include mapping historical data from their previous fraud studies into the model to identify any classification differences from their current systems. Others are evaluating modifications to their survey and/or research efforts.
- COVID-19 trends. While the ongoing pandemic has shifted fraud patterns and increased global fraud risk (Off-site), COVID-19 has become an unwelcome diversion. The findings of our engagements indicate FI operational staffs have prioritized running their financial institutions’ day-to-day and COVID-related initiatives, such as handling Economic Impact Payments (EIPs) for individuals and making Paycheck Protection Program (PPP) business loans. Projects to facilitate incremental improvements in fraud management may not have made the priority list these past months – but we like to think that as vaccinations roll out to the general public, work will resume to examine the model’s capabilities and how it can make a difference in their own organizations.
We are inspired by the enthusiastic reception and feedback we have heard from stakeholders across the payments ecosystem and are looking forward to continuing the dialogue. In addition to ongoing awareness and education, we plan to focus our discussions on how organizations plan to use – or have already adopted – the FraudClassifier model.
Our journey toward improving the U.S. payment system is rooted in collaboration between the Fed and the industry. Likewise, the industry’s journey to adopt the FraudClassifier model will benefit from conversations between the Fed, early adopters, fraud experts and other stakeholders on the various ways to adopt and benefit from the model. Stay tuned for updates.
Sharing and use of the FraudClassifier model throughout the industry is encouraged; any adoption of the FraudClassifier model is voluntary at the discretion of each individual entity. The FraudClassifier model is not intended to result in mandates or regulations, and does not give any legal status, rights or responsibilities, nor is the FraudClassifier model intended to define or imply liabilities for fraud loss or create legal definitions, regulatory or reporting requirements. Absent written consent, the FraudClassifier model may not be used in a manner that suggests the Federal Reserve endorses a third-party product or service.