Finance Foundation Models

Summary: A new class of proprietary foundation models trained on financial transaction data, delivering step-change uplifts over bespoke ML models across credit, fraud, and personalization.

Sources: raw/articles/simon-taylor-2026-04-26.md, raw/call-notes/carlos-2026-05-10.md, raw/call-notes/shrikant-2026-05-11.md

Last updated: 2026-05-17


Overview

Finance foundation models are transformer-based models trained on large corpora of financial behavioral data (transactions, events, clickstreams) rather than text. They are not LLMs — they don’t generate language, and they don’t compete with GPT or Claude. They learn dense representations of customer behavior that can be fine-tuned across multiple downstream tasks.

The analogy: what BERT did for text in 2020, these models are now doing for financial event sequences.

Known Models (as of 2026)

ModelCompanyTraining DataKey Results
PRAGMARevolut24B banking events, 26M customers, 111 countries+130% credit scoring, +65% fraud recall
nuFormerNubank100B+ transactions, 100M+ customersGPT-like architecture; narrower use cases
LTMMastercardBillions of card transactionsCyber risk identification
UPI HelpNPCI (India)UPI transactionsFine-tuned Mistral 24B; conversational agent for 400M+ UPI users
Nemo-4-PayPalPayPalPayPal shopping dataFine-tuned llama3.1-nemotron-nano-8B-v1; 45% cheaper to run; 2 weeks of fine-tuning

Why Behavioral Data is Powerful

Pavel Nesterov (PRAGMA author, ex-ad-tech): in ad-tech, 50 clicks plus links visited was enough to estimate a person’s age, income, and number of children. The same principle applies to banking event sequences — behavioral features contain almost everything.

This is the same insight that makes Google and Meta so powerful. Revolut is applying it to banking data.

What These Models Replace

A single foundation model replaces multiple bespoke ML models, each hand-crafted by a data science team:

  • Credit scoring models
  • Fraud detection models
  • Marketing/propensity models
  • Product recommendation models
  • Churn models

The key shift: instead of building a new model per task, fine-tune one foundation model per task using LoRA. This is dramatically faster and often outperforms the specialized models.

Competitive Implications

  • Custom finance foundation models = proprietary IP moat
  • Banks with better behavioral embeddings will price credit more aggressively, catch more fraud, and cross-sell more effectively
  • This compounds: the more customers, the better the model, the better the outcomes, the more customers
  • Traditional banks have the data but not the execution speed; neobanks have the speed

Why Banks Haven’t Done This Yet

  1. Execution culture — traditional banks move slowly; committee-based decisions, formal change management
  2. Data infrastructure — modern ML pipelines require clean, accessible data; legacy banks spend months just finding and scrubbing training data
  3. Risk aversion — 99% accuracy required vs. 95% acceptable at tech-first firms (source: carlos-call)
  4. Explainability concerns — regulators require interpretability for credit decisions; Shrikant noted this specifically for decisioning teams (source: shrikant-call, jie-capital-one-call)

What’s Coming

The generative version: a model that doesn’t just predict a customer’s next action but generates the full sequence of future events. This enables:

  • Simulating when a customer will take a product
  • Identifying what conditions lead to that decision
  • Engineering those conditions

Infrastructure

See nvidia-finance for the tooling stack (H100s, NeMo AutoModel, cuDF, TensorRT-LLM).