🌊
Flow Matching Market Studio v1.0 Live

Continuous Normalizing Flows & Neural ODEs for Market Microstructure

Flow Matching Hyperparameters

Neural ODE Velocity Field & Coupling Configuration

Regime:
Coupling:
ODE Solver:
Integration Steps (NFEs): 8
Volatility Scale ($\sigma$): 0.30
Tail Heaviness ($\nu$ df): 3.5
Particle Paths: 80 Trajectories

Continuous Probability Flow ODE: $x_t \in [p_0, p_1]$

Displacement paths from standard Gaussian prior $p_0$ ($t=0$) to target empirical density $p_1$ ($t=1$).

OT Geodesic Straightness: 98.4%

Velocity Vector Field $v_\theta(x, t)$

Instantaneous phase direction $\frac{dx}{dt}$ across state-time space.

Optimal Transport Continuity Equation:

$$\partial_t p_t(x) + \nabla \cdot (p_t(x) v_t(x)) = 0, \quad \psi_t(x_0 \mid x_1) = (1 - t) x_0 + t x_1$$

Loss: $\mathcal{L}_{\text{FM}} = \mathbb{E}[\| v_\theta(x_t, t) - (x_1 - x_0) \|^2]$
Sampling: $x_{t+h} = \text{RK4}(x_t, v_\theta, h)$