



















Abstract:We study the detection of transient liquidity erosion ("crumbling quotes") in electronic limit order books, where observable quote deterioration may reflect either mechanical liquidity withdrawal or informational repricing. Using the ABIDES agent-based simulator, we construct a multi-agent environment in which crumbling emerges from stochastic regime switches in a market maker, providing time-resolved ground truth unavailable in real market data. We develop a detection pipeline that identifies mechanically driven quote erosion using order book features, and train a neural model to produce calibrated crumbling probabilities. Experiments demonstrate that the proposed framework reliably identifies crumbling events against agent-level ground truth, with the neural model achieving +36% AUC improvement over rule-based baselines and robust performance across normal, high-volatility, bull, and bear market conditions. Ablation studies on temporal features and varying the dependence structure of the ground-truth mechanism confirm that the framework generalizes across both independent and autocorrelated liquidity withdrawal dynamics.
| Comments: | 10 pages, 4 figures. Accepted at ICLR 2026 Workshop on Advances in Financial AI |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.21993 [cs.LG] |
| (or arXiv:2604.21993v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.21993 arXiv-issued DOI via DataCite (pending registration) |
From: Haohan Xu [view email]
[v1]
Thu, 23 Apr 2026 18:22:52 UTC (2,052 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。