Revolut enhances fraud detection with PRAGMA model on Nvidia platform

Jun. 25, 2026

Revolut just built what might be the most ambitious AI model purpose-built for banking. Called PRAGMA, short for PRe-trained Banking Foundation Model, it’s a series of transformer-based models developed in collaboration with Nvidia that aims to handle fraud detection, credit scoring, and other financial tasks through a single unified system rather than a patchwork of specialized tools.

PRAGMA was trained on roughly 40 billion banking events sourced from approximately 25 million Revolut users spread across 111 countries, amounting to 207 billion tokens.

Traditional fraud detection in banking relies on stacking multiple machine learning models, each trained for a narrow task. PRAGMA uses masked modeling techniques on tokenized sequences of user interactions, then applies that understanding across multiple tasks simultaneously.

The results on Revolut’s internal benchmarks suggest this unified approach pays off. The model demonstrated a 64.7% improvement in fraud recall and a 16.7% increase in fraud precision compared to the company’s existing specialized systems.

Credit scoring saw even more dramatic gains. PRAGMA achieved up to a 130% uplift in PR-AUC metrics.

PRAGMA runs on Nvidia’s H100 GPUs within the Nebius AI Cloud infrastructure. The model comes in multiple sizes, ranging from 10 million parameters up to 1 billion parameters.

The largest variant, PRAGMA-L at 1 billion parameters, was trained using up to 64 Nvidia H100 GPUs. The smaller variants at 10 million and 100 million parameters are specifically optimized for real-time inference.

The research paper detailing PRAGMA was submitted on April 9, 2026, and presented at Nvidia’s GTC 2026 conference. Key contributors include members of Revolut’s Research team alongside Nvidia engineers, with particular emphasis on self-supervised training techniques that reduce the need for manually labeled data.

Revolut reports that the approach has decreased its dependency on traditionally engineered features — those handcrafted data inputs that require domain experts to design and maintain.