{"paper_id":"2512.18648","title":"Optimal Signal Extraction from Order Flow: A Matched Filter Perspective on Normalization and Market Microstructure","authors":["Sungwoo Kang"],"paper_date":"2025-12-21","paper_type":"survey-review","paper_url":"https://arxiv.org/pdf/2512.18648v2","page_url":"https://thequant.space/flowcharts/optimal-signal-extraction-from-order-flow-a-matched-filter/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a general matched filter principle for order flow normalization, matching the scaling behavior of the signal-generating process.","quote":"We establish a general matched filter principle for order flow normalization: optimal normalization must match the scaling behaviour of the signal-generating process.","summary":"We demonstrate that the choice of normalization for order flow intensity is fundamental to signal extraction in finance, not merely a technical detail. Through theoretical modeling, Monte Carlo simulation, and empirical validation using Korean market data, we prove that market capitalization…","strategy":"Market-cap normalized long‑short portfolio (SMC signal)"},"assumptions":{"status":"available","items":[{"assumption":"Daily turnover is heteroskedastic, providing the heteroskedasticity central to the theoretical model.","type":"market","stated":"explicit","quote":"Daily turnover exhibits substantial cross-sectional variation (mean 2.6%, std 10.9%), providing the heteroskedasticity central to our theoretical model."},{"assumption":"Order flow scaling differs across investor types (capacity‑scaled vs volume‑scaled).","type":"model","stated":"explicit","quote":"the direction of normalization dominance should reverse across investor types whose scaling behaviours differ."},{"assumption":"The KRX daily disclosures accurately capture net order flow by investor category.","type":"data","stated":"explicit","quote":"All data sourced from Korea Exchange (KRX) daily disclosures and CREON market data."},{"assumption":"Signal extraction can be framed as SNR maximization using Jensen’s inequality.","type":"other","stated":"explicit","quote":"deriving the general matched filter principle from Jensen’s inequality and SNR maximization"},{"assumption":"Monte Carlo simulations with 500 stocks each approximate real‑world heterogeneity.","type":"other","stated":"implied","quote":"We validate these predictions through 1,000 Monte Carlo simulations with 500 stocks each"},{"assumption":"Fama‑MacBeth standard errors provide valid inference for the regressions.","type":"statistical","stated":"implied","quote":"t‑statistics in parentheses from Fama‑MacBeth time‑series standard errors"}]},"datasets":{"status":"available","items":[{"name":"Korean market order flow data","provider":"Korea Exchange (KRX)","kind":"order-book","access":"public","period":"2020–2024","universe":"Korean equities","quote":"2.7 million stock‑day observations from the Korean market (2020–2024)."},{"name":"CREON market data","provider":"CREON","kind":"market-prices","access":"commercial","period":"2020–2024","universe":"Korean equities","quote":"All data sourced from Korea Exchange (KRX) daily disclosures and CREON market data."}],"known":[],"sample":{"start":"2020","end":"2024","market":"Korean equity market","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":"These are gross, pre‑transaction‑cost Sharpe ratios assuming frictionless daily rebalancing; actual implementable Sharpe ratios would be substantially lower after accounting for bid‑ask spreads, market impact, and short‑selling costs.","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"These are gross, pre‑transaction‑cost Sharpe ratios assuming frictionless daily rebalancing; actual implementable Sharpe ratios would be substantially lower after accounting for bid‑ask spreads, market impact, and short‑selling costs.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Monte Carlo simulations show matched‑filter normalizations achieve up to 1.99× higher signal correlation.","kind":"theoretical","quote":"Monte Carlo simulations confirm this principle works bidirectionally, with matched filters achieving up to 1.99×"},{"finding":"Domestic institutional net order flow normalized by market cap predicts next‑day returns (t = 9.65, p < 0.001).","kind":"predictive-accuracy","quote":"domestic institutional flows predict next‑day returns significantly under SMC (t = 9.65)"},{"finding":"Foreign institutional net order flow normalized by trading value predicts next‑day returns (t = 16.35, p < 0.001).","kind":"predictive-accuracy","quote":"foreign flows exhibit stronger predictability under STV (t = 16.35)"},{"finding":"Market‑cap normalization yields R² = 0.29% versus 0.14% for trading‑value normalization (≈2.07× higher).","kind":"performance","quote":"The empirical R2 ratio (0.29%/0.14% = 2.07×) is broadly consistent with, and somewhat exceeds, this prediction"},{"finding":"Long‑short portfolio based on SMC achieves annualised Sharpe 5.48 and mean daily return 15.84 bps (t = 12.11), outperforming STV (Sharpe 3.29, 8.41 bps).","kind":"performance","quote":"The SMC portfolio achieves an annualised Sharpe ratio of 5.48 with mean daily return of 15.84 Basis Points (bps) (t = 12.11), substantially outperforming the STV portfolio (Sharpe 3.29, 8.41 bps daily)."}],"reported_performance":{"strategy":"Market-cap normalized long‑short portfolio (SMC signal)","sharpe":5.48,"sharpe_benchmark":null,"annual_return_pct":39.84,"total_return_pct":null,"max_drawdown_pct":8.23},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"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":"2026-11-14T17:18:26Z"},"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/"}