🪙

Transaction Foundation Model

Card networks and issuers run separate models for fraud scoring, next-merchant prediction, amount forecasting, dispute triage, and collections prioritization. Each has its own pipeline. This demo collapses them into a shared model with multiple surfaces. The default tab returns four signals from a single read of the customer's transaction history in around 22 milliseconds: fraud probability, next merchant, amount range, and MCC enrichment. The other tabs run alternate surfaces on the same model: dispute triage, collections prioritization, and fraud-pattern attribution. Adding chargeback likelihood or decline reason is a configuration change. Not a new model build. A stage-1 self-supervised pretraining step also lets the encoder catch roughly 5× more fraud on a newly onboarded entity with almost no label history — a synthetic-data demonstration shown in the Cold Start tab.

Four signals from one read of the customer. Fraud probability, next merchant, amount range, and MCC enrichment come back together in around 22 milliseconds.
Many surfaces, one model. Dispute triage, collections prioritization, and fraud-pattern attribution run on the same shared model. Switching surfaces is instant. Adding a new one is a configuration change.
Reads the sequence, not just the row. Catches multi-transaction patterns flat-feature models miss. Card-testing bursts, account-takeover transitions, friendly-fraud trajectories.
Grounded analyst explanations. Each prediction comes with a cited explanation suitable for the analyst note. Free-text analyst questions are on the roadmap.

The Problem

Card networks and issuers maintain separate models for fraud scoring, next-merchant prediction, amount forecasting, and MCC enrichment. Each is its own pipeline, its own deployment, and its own inference cost. Discrete transaction features don't fit cleanly into a text-only LLM either.

How LFM Compares

Per-task gradient-boosted trees or transformer heads, each trained from scratch on tabular features. No shared representation across tasks. Every new business objective is a new model.

What LFM Unlocks

One model where today there are five or more. Fraud, dispute, collections, and fraud-pattern attribution share the same foundation, the same deployment, and the same audit trail. Adding chargeback likelihood, decline reason, or a new customer-segment signal is a configuration change. Every prediction also ships with a cited explanation suitable for an analyst note. Free-text analyst questions are on the roadmap.

Transaction historyLiquid Payments modelFraud · Merchant · Amount · MCC
Four signals from one read of the customer, in around 22 milliseconds. Other tabs above run alternate surfaces (dispute, collections, fraud pattern) on the same model.

Customer Archetype

Loading archetypes…
Select an archetype to run multi-head inference.

This demo is fine-tuned on sample data. Results improve with your data.