Division 02 / Fin-Tech

Continuous-time risk analytics
that adapt when markets break.

The Fin-Tech division of Stokhos Labs builds Neural Stochastic Differential Equation models that forecast the U.S. Treasury yield curve across every market regime, with 64.3% lower forecast error when financial panic strikes.

64.3%
MSE Reduction
vs. ARX-GARCH during financial panic
Time Resolution
continuous-time SDE vs. discrete steps
11
Yield Maturities
1M · 3M · 6M · 1Y · 2Y · 3Y · 5Y · 7Y · 10Y · 20Y · 30Y U.S. Treasury
How It Works

Neural SDEs: a model
built for real markets.

∂t
Continuous-Time Dynamics

The model evolves through a differential equation that responds instantaneously to new data, not once per day, but continuously.

gφ
Learned Uncertainty

The diffusion network learns state-dependent volatility from data. Uncertainty widens automatically in stress, with no manual recalibration.

Empirically Validated

Trained on all available FRED data, stress-tested on the March 2020 financial panic. ARX-GARCH MSE: 1.943. Neural SDE MSE: 0.692. A 64.3% reduction, zero retraining.

Request Access

Carry interest rate risk? Let's talk.

Banks, insurers, asset managers, and pension funds: reach out to discuss a pilot or research collaboration.