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.
Neural SDEs: a model
built for real markets.
The model evolves through a differential equation that responds instantaneously to new data — not once per day, but continuously.
The diffusion network learns state-dependent volatility from data. Uncertainty widens automatically in stress — no manual recalibration.
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.
Explore the platform.
Why ARX-GARCH and discrete-time models fail precisely when risk management matters most.
Read more →Drift networks, diffusion networks, and Euler–Maruyama integration: how the Neural SDE works.
Read more →Yield curve forecast vs. actual, cumulative error, and regime classification: the live product interface.
View dashboard →Built by Cole Amaya and Filip Maleev, researchers who understand both the mathematics and the market.
Meet the team →