Feedzai has launched RiskFM (Risk Foundation Model), the industry’s first Tabular Foundation Model purpose-built for financial data and risk decisioning.
The launch of RiskFM represents a fundamental shift in how financial crime is detected and prevented. For decades, institutions have relied on rules and manually engineered machine learning models built one customer at a time. RiskFM is designed to change that, offering a purpose-built frontier model that spans fraud detection, anti-money laundering (AML), and broader risk decisions across the entire financial crime lifecycle.
Feedzai is a global financial crime prevention company that annually risk-assesses $9tn in payments across 120bn events worldwide. Its platform spans the entire financial risk lifecycle, from onboarding and digital activity to card payments and real-time transfers — a breadth of data that the company says makes RiskFM uniquely positioned to be tested at scale as a holistic model rather than siloed in a single specialised application.
RiskFM has been trained on a broad, deep, and global dataset spanning onboarding, digital activity, payments, transfers, and AML workflows. Unlike existing industry attempts limited to card network data, this foundation model enables institutions to detect, prevent, and adapt to financial crime with greater speed and precision. The model is already demonstrating it can match the performance of bespoke supervised models using data from a single customer, and surpasses them when trained across multiple institutions and geographies — delivering faster deployment times and significantly lower implementation and maintenance costs.
Feedzai highlights three core capabilities that set RiskFM apart. First, compounding intelligence: when trained across multiple institutions and geographies simultaneously, RiskFM outperforms traditional models based on Gradient Boosting and Deep Learning approaches, continuing to improve as it ingests more data. Second, out-of-the-box performance: when used to power a bespoke model for a single customer, it matches highly tuned supervised models without the need for manual, time-consuming feature engineering. Third, breadth of coverage: RiskFM serves as the foundational AI layer for financial risk, designed to expand from mule account detection through to AML, providing institutions with a scalable model that grows with their needs.
Feedzai is currently working with early adopters to validate the initial RiskFM frameworks, with plans to scale these methodologies to large datasets and ultimately integrate them across its full suite of use cases.
The launch comes as the broader AI industry grapples with the limitations of large language models (LLMs) in financial settings. While LLMs have effectively addressed domains such as language, audio, and video — environments constrained by finite grammar and causality — financial transactions operate in a fundamentally different reality, where patterns are far less predictable and the domain is inherently adversarial.
Feedzai chief science officer Pedro Bizarro said, “Next transactions are far less predictable than the next word in a sentence. Consumer spending habits, payment types, and fraud modes change continuously. More importantly, financial risk is an adversarial domain; fraudsters actively adapt to evade detection in real-time.”
IDC research director, risk, financial crime, and compliance Sam Abadir said, “Foundation models have reshaped language, vision, and audio, but financial crime has remained stubbornly resistant to that wave. Feedzai’s RiskFM is a credible attempt to close that gap. The ability to match bespoke supervised models out of the box, without manual feature engineering, has real implications for how institutions think about deployment speed, cost, and coverage across the full financial crime lifecycle, from card fraud to AML. The early performance data is worth watching, as is how the model holds up as it expands into more complex use cases.”
Feedzai chief product officer Pedro Barata said, “Our vision is coming true: this is not just another Large Tabular Model for a single data type. We’ve developed a foundation model for financial data that covers multiple use cases — from cards to real-time payments — and geographies, delivering strong performance from Day One at global scale. RiskFM proves our multi-year investment in foundation models is paying off. We’re not just part of the conversation; we’re defining how it applies to the complexities of global financial crime prevention.”
Keep up with all the latest FinTech news here
Copyright © 2026 FinTech Global
