Early Detection of Latent Microstructure Regimes in Limit Order Books

TL;DR

This paper introduces a method for early detection of latent microstructure regime changes in limit order books, providing theoretical guarantees and demonstrating superior performance over classical methods.

Contribution

It formalizes a three-regime causal model, establishes identifiability of the latent build-up phase, and proposes a trigger-based detector with proven lead-time guarantees.

Findings

Method achieves mean lead-time +18.6 timesteps with perfect precision.

Outperforms classical change-point and microstructure baselines in simulations.

Preliminary application to BTC/USDT data shows consistent positive lead-times.

Abstract

Limit order books can transition rapidly from stable to stressed conditions, yet standard early-warning signals such as order flow imbalance and short-term volatility are inherently reactive. We formalise this limitation via a three-regime causal data-generating process (stable $\to$ latent build-up $\to$ stress) in which a latent deterioration phase creates a prediction window prior to observable stress. Under mild assumptions on temporal drift and regime persistence, we establish identifiability of the latent build-up regime and derive guarantees for strictly positive expected lead-time and non-trivial probability of early detection. We propose a trigger-based detector combining MAX aggregation of complementary signal channels, a rising-edge condition, and adaptive thresholding. Across 200 simulations, the method achieves mean lead-time $+18.6 \pm 3.2$ timesteps with perfect precision and moderate coverage, outperforming classical change-point and microstructure baselines. A preliminary application to one week of BTC/USDT order book data shows consistent positive lead-times while baselines remain reactive. Results degrade in low signal-to-noise and short build-up regimes, consistent with theory.