{"paper_id":"2509.22985","title":"Forecasting Liquidity Withdraw with Machine Learning Models","authors":["Haochuan","Wang"],"paper_date":"2025-09-26","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2509.22985v1","page_url":"https://thequant.space/flowcharts/forecasting-liquidity-withdraw-with-machine-learning-models/","scores":{"empirical_rigor":8.5,"math_complexity":6,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes and evaluates a framework for forecasting liquidity withdrawal using a Liquidity Withdrawal Index and machine learning models.","quote":"We propose and evaluate a framework for forecasting liquidity withdrawal using Nasdaq MBO data and a Liquidity Withdrawal Index (LWI).","summary":"Liquidity withdrawal is a critical indicator of market fragility. In this project, I test a framework for forecasting liquidity withdrawal at the individual-stock level, ranging from less liquid stocks to highly liquid large-cap tickers, and evaluate the relative performance of competing model…","strategy":"XGBoost (boosted trees)"},"assumptions":{"status":"available","items":[{"assumption":"The Liquidity Withdrawal Index (LWI) is stationary, allowing autoregressive modeling without differencing.","type":"statistical","stated":"explicit","quote":"Across all four tickers, the ADF statistics are strongly negative with p-values near zero (Table 2), rejecting the unit root null. Thus, LWI is stationary, making it valid for autoregressive modeling without"},{"assumption":"Liquidity dynamics exhibit short‑memory, so only the first one or two lags are predictive.","type":"statistical","stated":"implied","quote":"Autocorrelation plots reveal significant dependence at the first one or two lags, followed by rapid decay. This pattern is consistent with a stationary but short-memory process."},{"assumption":"Linear AR(5) and HAR models capture short‑term linear dependence in liquidity withdrawal.","type":"model","stated":"explicit","quote":"We use AR(5), which provides a one-second lookback to capture short-term linear dependence in liquidity withdrawal."},{"assumption":"Walk‑forward cross‑validation with an embargo period prevents information leakage and mimics live deployment.","type":"data","stated":"explicit","quote":"We apply walk-forward cross-validation with an embargo period to prevent information leakage."},{"assumption":"The study focuses on a one‑hour window of order‑by‑order data, assuming that this slice is representative of broader market behavior.","type":"data","stated":"implied","quote":"For tractability, our study focuses on July 30, 2025, 14:00–15:00 ET, covering several actively traded symbols."}]},"datasets":{"status":"available","items":[{"name":"Nasdaq Market‑by‑Order (MBO) data","provider":"Databento","kind":"order-book","access":"commercial","period":"2025-07-30 14:00–15:00 ET","universe":"several actively traded U.S. equities (e.g., HIMS, NBIS, RKLB, SNAP)","quote":"MBO provides the full order flow — every add, cancel, replace, and trade message from the NASDAQ matching engine — at nanosecond resolution."}],"known":[],"sample":{"start":null,"end":null,"market":"Nasdaq stocks","asset_class":"equities","frequency":"intraday"},"data_resolution":"l2-book"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"XGBoost significantly outperforms AR/HAR at the 5‑second horizon, achieving R² above 0.90.","kind":"predictive-accuracy","quote":"XGBoost significantly outperforms AR/HAR at 5 s horizons, consistent with the growing role of non-linear structure in driving liquidity withdrawal."},{"finding":"Linear AR and HAR models are competitive at 1–2 s horizons, while no model provides robust predictability at 250 ms.","kind":"performance","quote":"Our comparisons suggest that AR/HAR are adequate at 1–2 s horizons, while boosted trees dominate at 5 s, and no model delivers robust predictability at 250 ms."},{"finding":"The Liquidity Withdrawal Index is stationary across all four tickers, validating autoregressive approaches.","kind":"statistical","quote":"Across all four tickers, the ADF statistics are strongly negative with p-values near zero (Table 2), rejecting the unit root null. Thus, LWI is stationary."}],"reported_performance":{"strategy":"XGBoost (boosted trees)","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":25,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:26:17Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}