{"paper_id":"2408.10016","title":"High-Frequency Trading Liquidity Analysis | Application of Machine Learning Classification","authors":["Sid Bhatia","Sidharth Peri","Sam Friedman","Michelle Malen"],"paper_date":"2024-08-19","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2408.10016v1","page_url":"https://thequant.space/flowcharts/high-frequency-trading-liquidity-analysis--application-of-m/","scores":{"empirical_rigor":7.5,"math_complexity":3,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a comprehensive framework for analyzing liquidity in high‑frequency trading markets using machine‑learning classification models.","quote":"This research presents a comprehensive framework for analyzing liquidity in financial markets, particularly in the context of high-frequency trading.","summary":"This research presents a comprehensive framework for analyzing liquidity in financial markets, particularly in the context of high-frequency trading. By leveraging advanced machine learning classification techniques, including Logistic Regression, Support Vector Machine, and Random Forest, the…","strategy":"Random Forest liquidity classification model"},"assumptions":{"status":"available","items":[{"assumption":"Liquidity metrics are derived from TAQ data and are suitable predictors for price movements.","type":"data","stated":"implied","quote":"The core aim of this project is to utilize TAQ data to compute liquidity measures that serve as predictors in a model designed to forecast price movements."},{"assumption":"Price movement direction can be modeled as a binary classification (Up or Down).","type":"model","stated":"explicit","quote":"The predictive model is approached as a classification problem where the main dependent variable is the price movement direction, categorized as Up or Down."},{"assumption":"Data are sampled only between 11:00 AM and 4:00 PM and aggregated to 1‑minute intervals.","type":"data","stated":"explicit","quote":"Data sampling includes daily subsets from 11:00 AM to 4:00 PM. This subset is further refined to 1‑minute frequency data"},{"assumption":"The dataset is split 70% training, 15% validation, 15% testing.","type":"model","stated":"explicit","quote":"Data will be split in a 70%-15%-15% manner across training, validation, and testing sets respectively."},{"assumption":"All available liquidity variables are initially used for model fitting before subset selection.","type":"model","stated":"explicit","quote":"Initially, all models are fitted with all available independent variables."},{"assumption":"High‑frequency data are taken from the Refinitiv Tick History Dataset.","type":"data","stated":"explicit","quote":"This research agenda involves using limit order book datasets to develop predictive models for price movements, utilizing high-frequency data from the Refinitiv Tick History Dataset."}]},"datasets":{"status":"available","items":[{"name":"Trade and Quote (TAQ) data","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":null,"quote":"The core aim of this project is to utilize TAQ data to compute liquidity measures that serve as predictors in a model designed to forecast price movements.","known_id":"taq"},{"name":"Refinitiv Tick History Dataset","provider":"Refinitiv","kind":"order-book","access":"commercial","period":null,"universe":null,"quote":"This research agenda involves using limit order book datasets to develop predictive models for price movements, utilizing high-frequency data from the Refinitiv Tick History Dataset.","known_id":"refinitiv"}],"known":[{"id":"refinitiv","name":"Refinitiv / LSEG (Datastream, Eikon, Tick History)","provider":"LSEG","kind":"market-prices","access":"commercial","quote":"3 Research Agenda 3.1 Study Objectives This research agenda involves using limit order book datasets to develop predictive models for price movements, utilizing high-frequency data from the Reﬁnitiv Tick History Dataset.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":"US equities (TAQ data)","asset_class":"equities","frequency":"intraday"},"data_resolution":"unclear"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"no","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"Random Forest achieved the highest predictive accuracy among the three classifiers.","kind":"performance","quote":"Notably, the Random Forest algorithm outperformed others, delivering the highest accuracy in our predictions."},{"finding":"Using all liquidity metrics yields higher accuracy than models with a reduced subset of features.","kind":"predictive-accuracy","quote":"Key insights from these results include the notably high accuracy of the baseline models compared to the tuned models that utilized a subset of liquidity metrics."},{"finding":"Liquidity Ratio, Flow Ratio, and Turnover consistently rank as the most important features across all models.","kind":"statistical","quote":"Flow Ratio, and Turnover consistently emerge as significant across all models."}],"reported_performance":{"strategy":"Random Forest liquidity classification model","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":24,"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":"2026-11-14T18:04:00Z"},"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/"}