Early Detection of Latent Microstructure Regimes in Limit Order Books

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hiremath, Prakul Sunil, Hiremath, Vruksha Arun
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913056359972864
author Hiremath, Prakul Sunil
Hiremath, Vruksha Arun
author_facet Hiremath, Prakul Sunil
Hiremath, Vruksha Arun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20949
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Early Detection of Latent Microstructure Regimes in Limit Order Books
Hiremath, Prakul Sunil
Hiremath, Vruksha Arun
Machine Learning
Trading and Market Microstructure
Methodology
I.2.6; G.3; J.1
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.
title Early Detection of Latent Microstructure Regimes in Limit Order Books
topic Machine Learning
Trading and Market Microstructure
Methodology
I.2.6; G.3; J.1
url https://arxiv.org/abs/2604.20949