Learning Time-Inhomogeneous Markov Dynamics in Financial Time Series via Neural Parameterization

TL;DR

This paper introduces a neural network-based framework for modeling non-stationary Markov dynamics in financial time series, balancing interpretability with complex regime detection.

Contribution

It proposes a method to parameterize time-varying Markov transition matrices with neural networks while maintaining structural interpretability.

Findings

Learned operators capture complex regime shifts in financial data.

State-conditioned model achieves mean row heterogeneity of 0.0073.

Operator row entropy correlates with realized variance at -0.62.

Abstract

Modeling the dynamics of non-stationary stochastic systems requires balancing the representational power of deep learning with the mathematical transparency of classical models. While classical Markov transition operators provide explicit, theoretically grounded rules for system evolution, their empirical estimation collapses due to severe data sparsity when applied to high-resolution, high-noise environments. We explore this statistical barrier using financial time series as a canonical, real-world testbed. To overcome the degeneracy of empirical counting, we introduce a framework that utilizes neural networks strictly as parameterization engines to generate explicit, time-varying Markov transition matrices. By constraining the neural network to output its predictions as a formal stochastic operator, we maintain complete structural interpretability. We demonstrate that these learned operators successfully capture complex regime shifts: the state-conditioned model achieves mean row heterogeneity $\bar{\rho} = 0.0073$ while the state-free ablation collapses to exactly zero, and operator row entropy correlates with realized variance at $r = -0.62$ ($p \approx 10^{-251}$), revealing that high-volatility regimes homogenize transition dynamics rather than diversify them. Furthermore, rather than enforcing the Chapman-Kolmogorov equations as a rigid structural requirement, we repurpose them as a localized diagnostic tool to pinpoint specific temporal windows where first-order memory assumptions break down. Ultimately, this framework demonstrates how neural networks can be constrained to make rigorous, classical operator analysis viable for complex real-world time series.