{"paper_id":"2503.18199","title":"Generating realistic metaorders from public data","authors":["Guillaume Maitrier","Grégoire Loeper","Jean-Philippe Bouchaud"],"paper_date":"2025-03-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2503.18199v2","page_url":"https://thequant.space/flowcharts/generating-realistic-metaorders-from-public-data/","scores":{"empirical_rigor":6,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel algorithm to generate realistic metaorders from publicly available trade data.","quote":"This paper introduces a novel algorithm for generating realistic metaorders from public trade data","summary":"This paper introduces a novel algorithm for generating realistic metaorders from public trade data, addressing a longstanding challenge in price impact research that has traditionally relied on proprietary datasets. Our method effectively recovers all established stylized facts of metaorders…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"A metaorder is defined as a sequence of trades of the same sign initiated by a given trader within the same trading session.","type":"other","stated":"explicit","quote":"We define a metaorder as a sequence of trades of the same sign initiated by a given trader within the same trading session."},{"assumption":"The mapping function can be specified with only two degrees of freedom (number of traders and their trading frequency) and still recover the correct impact.","type":"model","stated":"explicit","quote":"We gave this mapping function only two degrees of freedom: the number of different traders in a given day and the distribution of their trading frequency"},{"assumption":"Public trade data (e.g., from a single exchange) contain enough information to reconstruct synthetic metaorders that preserve real‑world stylized facts.","type":"data","stated":"implied","quote":"Our method effectively recovers all established stylized facts of metaorders impact"},{"assumption":"Daily traded volume (VD) and intraday volatility (σD) can be computed and used as proxies for market liquidity and risk.","type":"market","stated":"explicit","quote":"Compute daily traded volume VD and intraday volatility σD, which we define for"},{"assumption":"Impact is independent of metaorder duration because the volatility contribution scales as √T while volume scales as T, cancelling T in the impact formula.","type":"other","stated":"explicit","quote":"the volatility contribution scales as √T whereas the total traded volume scales as T, which means that the explicit T dependence cancels from I(Q)"}]},"datasets":{"status":"available","items":[{"name":"public trade data","provider":null,"kind":"order-book","access":"public","period":null,"universe":null,"quote":"Our method effectively recovers all established stylized facts of metaorders impact"},{"name":"BNP Paribas share price data","provider":"BNP Paribas","kind":"market-prices","access":"public","period":null,"universe":null,"quote":"Synthetic metaorders were generated with BNP Paribas share price"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"tick"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"n/a","evidence_card":"no","evidence_card_quoted":true},"conflict_kind":"applicability","card_detail":null,"card_quote":"Neglecting such costs can easily turn a profitable strategy on paper into a money losing machine","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"execution-cost","findings":[{"finding":"The synthetic metaorders generated by the algorithm reproduce all major stylized facts: the Square Root Law, its independence from duration, concave execution profiles, and slow power‑law decay.","kind":"statistical","quote":"Using this algorithm, we were able to recover all the salient stylized facts reported in the existing literature, specifically: the Square Root Law and its independence with respect to metaorder duration; the concave profile during metaorder execution; and the slow power-law decay after execution."},{"finding":"Impact of synthetic metaorders is independent of metaorder duration, with an average prefactor Y ≈ 0.6 for durations longer than ~30 seconds.","kind":"statistical","quote":"The blue dots represent the impact divided by the volume contribution as a function of duration, which is approximately constant for T ≳30 seconds, and on average equal to Y = 0.6."},{"finding":"The post‑execution decay of synthetic metaorders matches the propagator model with decay exponent β ≈ 0.2.","kind":"theoretical","quote":"Figure 5: Price relaxation post metaorder execution, well fitted by the impact predicted by the propagator model, with the value β ≈0.2."},{"finding":"Synthetic metaorders show no correlation with short‑term predictive signals, supporting a mechanical origin of price impact.","kind":"theoretical","quote":"By construction, a synthetic metaorder has no connection to a trader’s intention to trade based on a predictive signal. Yet, its impact is indistinguishable from that of a real metaorder"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":16,"citations":{"cited_by_in_corpus":7,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":2,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":4},"independent_papers":[{"paper":{"paper_id":"2602.19590","title":"Metaorder modelling and identification from public data","paper_date":"2026-02-23","authors":["Ezra Goliath","Tim Gebbie"],"empirical_rigor":7.5,"page_url":"https://thequant.space/flowcharts/metaorder-modelling-and-identification-from-public-data/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2510.27334","title":"When AI Trading Agents Compete: Adverse Selection of Meta-Orders by Reinforcement Learning-Based Market Making","paper_date":"2025-10-31","authors":["Ali Raza Jafree","Konark Jain","Nick Firoozye"],"empirical_rigor":3,"page_url":"https://thequant.space/flowcharts/when-ai-trading-agents-compete-adverse-selection-of-meta-or/"},"how":"uses_method_or_data","quote":null}],"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":"2026-11-14T17:42:14Z"},"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/"}