{"paper_id":"2405.08101","title":"Data-driven measures of high-frequency trading","authors":["G. Ibikunle","B. Moews","D. Muravyev","K. Rzayev"],"paper_date":"2024-05-13","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2405.08101v3","page_url":"https://thequant.space/flowcharts/data-driven-measures-of-high-frequency-trading/","scores":{"empirical_rigor":8,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes novel data‑driven measures of high‑frequency trading that separate liquidity‑supplying and liquidity‑demanding strategies, using machine‑learning models trained on proprietary data and applied to public intraday data.","quote":"We develop novel data-driven measures of HFT activity that separate strategies that supply and demand liquidity.","summary":"High-frequency trading (HFT) accounts for almost half of equity trading volume, yet it is not identified in public data. We develop novel data-driven measures of HFT activity that separate strategies that supply and demand liquidity. We train machine learning models to predict HFT activity observed…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The mapping learned from the 2009 Nasdaq sample remains informative for other U.S. stocks and later dates.","type":"model","stated":"explicit","quote":"This step assumes that the Nasdaq mapping remains informative for other U.S. stocks and later dates."},{"assumption":"HFT activity is endogenous to liquidity and trading characteristics, requiring instrumental variables for identification.","type":"statistical","stated":"explicit","quote":"HFT activity is endogenous to the liquidity and trading characteristics that may also shape information acquisition."},{"assumption":"The proprietary Nasdaq HFT dataset accurately identifies aggressive (HH, HN) and passive (HH, NH) trades.","type":"data","stated":"explicit","quote":"Trades are classified as HH when both parties are HFTs, HN when an HFT demands liquidity from a non-HFT, NH when a non-HFT demands liquidity from an HFT, and NN when neither party is an HFT."},{"assumption":"Public intraday variables (24 TAQ indicators) contain enough information to predict observed HFT shares.","type":"model","stated":"implied","quote":"inputs to predict the observed HFT shares in the Nasdaq sample."},{"assumption":"Tree‑based ensemble methods (extremely randomized trees) provide accurate out‑of‑sample predictions of HFT activity.","type":"model","stated":"explicit","quote":"Extremely randomized trees provide the highest out-of-sample accuracy with low dispersion; therefore, we use them for the main measures."},{"assumption":"Spread variables can be excluded from the feature set without materially altering the HFT measure predictions.","type":"statistical","stated":"explicit","quote":"To account for spread variables appearing in the training feature set, we also reconstruct the HFT measures by excluding them; the spread results remain similar."}]},"datasets":{"status":"available","items":[{"name":"Nasdaq HFT dataset","provider":"Nasdaq","kind":"order-book","access":"proprietary","period":"2009","universe":"120 stocks","quote":"The first is the Nasdaq HFT dataset used by Brogaard et al. (2014), which identifies the parties to each trade for 120 stocks in 2009 and reports time to the millisecond, price, volume, trade direction, and counterparty type."},{"name":"WRDS TAQ Intraday Indicators","provider":"WRDS","kind":"market-prices","access":"public","period":"2010‑2023","universe":"U.S. stock universe","quote":"The second source is WRDS TAQ Intraday Indicators for the same period. We select 24 public variables covering prices, trading volume, trading costs, liquidity, and volatility.","known_id":"taq"},{"name":"LSEG Datascope Tick History","provider":"LSEG","kind":"order-book","access":"commercial","period":null,"universe":null,"quote":"Conventional HFT proxies are constructed from quote-level Millisecond TAQ data. Intraday transactions and corresponding bid and ask quotes come from LSEG Datascope Tick History.","known_id":"refinitiv"},{"name":"I/B/E/S announcements","provider":"I/B/E/S","kind":"fundamentals","access":"commercial","period":null,"universe":null,"quote":"Earnings and merger-and-acquisition announcement dates come from I/B/E/S and the Thomson Reuters Securities Data Company database, respectively.","known_id":"ibes"},{"name":"CRSP stock returns and volume","provider":"CRSP","kind":"market-prices","access":"commercial","period":null,"universe":null,"quote":"Stock returns and trading volume come from CRSP.","known_id":"crsp"},{"name":"Eurofidai‑Bedofih data","provider":"Eurofidai‑Bedofih","kind":"order-book","access":"proprietary","period":null,"universe":"Euronext Paris stocks","quote":"Finally, proprietary Eurofidai‑Bedofih data identify HFT activity in Euronext Paris stocks; Section 5 describes that sample."}],"known":[{"id":"taq","name":"NYSE TAQ","provider":"NYSE","kind":"market-prices","access":"commercial","quote":"2 Given that the input public variables can be computed for any TAQ stock-day, we use the trained mapping to construct daily measures of liquidity-supplying and liquidity-demanding HFT for 8,314 U.S. stocks from 2010 to 2023.","mentions":7,"used_in":3},{"id":"refinitiv","name":"Refinitiv / LSEG (Datastream, Eikon, Tick History)","provider":"LSEG","kind":"market-prices","access":"commercial","quote":"We construct the public input variables from LSEG Datascope rather than Eurofidai-Bedofih, following the same approach of constructing input features from non-proprietary data as in the U.S. analysis.","mentions":5,"used_in":2},{"id":"wrds","name":"WRDS","provider":"Wharton Research Data Services","kind":"other","access":"commercial","quote":"Following Bogousslavsky et al. (2024), we use the precomputed WRDS measures to improve replicability and limit researcher discretion.","mentions":2,"used_in":1},{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"Stock returns and trading volume come from CRSP.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"tick"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R4a","candidates":{"front_matter":"n/a","evidence_card":"partial","evidence_card_quoted":true},"card_detail":"Spreads are used as an outcome variable; a one‑standard‑deviation increase in liquidity‑supplying HFT reduces spreads by 28%, while the same increase in liquidity‑demanding HFT raises spreads by 38%. The analysis also re","card_quote":"A one-standard-deviation increase in liquidity-supplying HFT corresponds to 28% lower spreads, while the same increase in liquidity-demanding HFT corresponds to 38% higher spreads.","meaning":"the paper reports no trading or execution result; the cost the extractor found is a model parameter"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The ML‑generated HFT measures outperform five conventional public‑data proxies in capturing both cross‑sectional differences and time‑series variation of liquidity‑demanding and liquidity‑supplying HFT.","kind":"predictive-accuracy","quote":"the ML predictions better capture both cross-sectional differences and time-series variation in liquidity-demanding and liquidity-supplying HFT."},{"finding":"Liquidity‑supplying HFT improves price discovery around earnings announcements, while liquidity‑demanding HFT impedes it.","kind":"statistical","quote":"Liquidity-supplying HFTs improve price discovery around earnings announcements while liquidity-demanding strategies impede it."},{"finding":"A one‑standard‑deviation increase in HFT demand reduces information acquisition by 18%, whereas the same increase in HFT supply raises information acquisition by 9%.","kind":"statistical","quote":"a one-standard-deviation increase in HFT demand corresponds to 18% less information acquisition, while the same increase in HFT supply corresponds to 9% more."},{"finding":"During the COVID‑19 crisis, liquidity‑supplying HFT remained resilient and its negative association with spreads strengthened.","kind":"performance","quote":"During COVID-19, liquidity-supplying HFT increased and its negative association with spreads strengthened, evidence consistent with resilient passive HFT during prolonged market stress."},{"finding":"Public proxies used in prior information‑acquisition literature mainly capture liquidity‑demanding HFT, reconciling earlier findings that aggregate algorithmic trading reduces information acquisition.","kind":"other","quote":"We show that Weller’s (2018) public proxies primarily capture HFT demand, helping reconcile his aggregate result with our findings."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"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":"2026-11-14T18:09:59Z"},"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/"}