Quantitative Risk Infrastructure

Continuous-time
risk analytics that
adapt when markets break.

Stokhos Labs builds Neural Stochastic Differential Equation models that forecast the U.S. Treasury yield curve with greater accuracy across all market regimes — and 64.3% lower forecast error when financial panic strikes.

U.S. TREASURY YIELD CURVE · MARCH 2020 REPRESENTATIVE DATA
Neural SDE Forecast
Actual
68% CI
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 — 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

Ready to see the platform in action?

Every institution that carries interest rate risk needs better yield curve analytics. Reach out to discuss a pilot.