Early Detection of Latent Microstructure Regimes in Limit Order Books

Paper: arXiv 2604.20949

Authors: Prakul Sunil Hiremath, Vruksha Arun Hiremath

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.

Complexity vs Empirical Score

• Math Complexity: 7.5/10
• Empirical Rigor: 8.0/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper combines rigorous derivation of identifiability and detection probability bounds with a robust empirical pipeline featuring 200 simulation runs and a pilot study on real-world BTC/USDT data.

Research Flowchart

  flowchart TD
    A[<b>Goal:</b> Early Detection of Latent Stress in LOBs] --> B[<b>Framework:</b> 3-Regime Causal DGP<br/>(Stable -> Latent Build-up -> Stress)]
    B --> C[<b>Data/Inputs:</b> Simulated Data & BTC/USDT<br/>Limit Order Book Data]
    C --> D[<b>Methodology:</b> Trigger-based Detector<br/>(MAX Aggregation + Adaptive Thresholding)]
    D --> E{<b>Computational Process:</b><br/>Identifiability & Lead-time Guarantees}
    E --> F[<b>Outcomes:</b> +18.6 Mean Lead-time<br/>with Perfect Precision]
    F --> G[<b>Limitation:</b> Degrades in low SNR<br/>or short build-up regimes]