English

Early Detection of Latent Microstructure Regimes in Limit Order Books

Machine Learning 2026-04-24 v1 Trading and Market Microstructure Methodology Machine Learning

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±3.2+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.

Keywords

Cite

@article{arxiv.2604.20949,
  title  = {Early Detection of Latent Microstructure Regimes in Limit Order Books},
  author = {Prakul Sunil Hiremath and Vruksha Arun Hiremath},
  journal= {arXiv preprint arXiv:2604.20949},
  year   = {2026}
}

Comments

48 pages, 7 figures. Combines theoretical guarantees (identifiability and early-detection bounds), 200-run simulation study, and preliminary real-data evaluation on BTC/USDT limit order books. Code and data available