Foundation models on enterprise event data.
Lyon builds private foundation models for banks, fintechs, funds, brokers and payments companies, turning their own data into better predictions.
These models apply the transformer technology behind large language models to transaction histories, loan records and customer activity. They learn relationships across events and over time that manually engineered features can miss, producing richer signals for existing models and new applications.
The same model can support fraud detection, credit default prediction, loss given default estimation and product recommendations. Lyon develops and deploys each institution’s model, with software to keep it current and integrate its predictions into existing systems.
At a consumer fintech with tens of millions of users, a Lyon model trained on tens of billions of transactions delivered a 112% relative improvement in default prediction PR-AUC over the fintech’s existing tree-based model.