{"paper_id":"2307.02375","title":"Online Learning of Order Flow and Market Impact with Bayesian Change-Point Detection Methods","authors":["Ioanna-Yvonni Tsaknaki","Fabrizio Lillo","Piero Mazzarisi"],"paper_date":"2023-07-05","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2307.02375v2","page_url":"https://thequant.space/flowcharts/online-learning-of-order-flow-and-market-impact-with-bayesia/","scores":{"empirical_rigor":7,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes Bayesian online change‑point detection methods with a novel score‑driven extension to identify regime shifts in real‑time and improve online predictions of order flow and market impact.","quote":"we propose the use of Bayesian online change-point detection (BOCPD) methods to identify regime shifts in real-time and enable online predictions of order flow and market impact.","summary":"Financial order flow exhibits a remarkable level of persistence, wherein buy (sell) trades are often followed by subsequent buy (sell) trades over extended periods. This persistence can be attributed to the division and gradual execution of large orders. Consequently, distinct order flow regimes…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Data are independently and identically distributed (i.i.d.) within each regime in the basic BOCPD model.","type":"statistical","stated":"explicit","quote":"In the BOCPD model, the data is assumed to be independently and identically distributed (i.i.d.) within each regime."},{"assumption":"Within each regime the observations follow a normal (Gaussian) distribution.","type":"statistical","stated":"explicit","quote":"Throughout the paper, we consider normal distributions. This assumption is tested using a Jarque-Bera (JB) statistic in the empirical application as shown in Section 4."},{"assumption":"Parameters (mean, variance, autocorrelation) are constant within each regime unless the score‑driven extension is used.","type":"model","stated":"explicit","quote":"At this stage, both BOCPD and MBO assume that parameters (i.e. mean, variance, autocorrelation) are constant within each regime."},{"assumption":"Markovian dynamics (serial correlation) may be present within regimes in the extended MBO model.","type":"model","stated":"explicit","quote":"we propose a new MBO algorithm that considers Markovian dynamics within each regime, thus allowing for serial correlation."},{"assumption":"Time‑varying autocorrelation can be captured by a score‑driven observation‑driven framework.","type":"model","stated":"explicit","quote":"... which provide an observation‑driven framework for real‑time learning of time‑varying parameters."}]},"datasets":{"status":"available","items":[{"name":"NASDAQ order flow data (TSLA, MSFT)","provider":"LOBSTER","kind":"order-book","access":"commercial","period":null,"universe":"Two liquid NASDAQ stocks (Tesla and Microsoft)","quote":"We present an empirical application of the proposed methods using order flow samples from stocks traded on NASDAQ.","known_id":"lobster"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"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":"The newly proposed score‑driven BOCPD model shows superior out‑of‑sample predictive performance compared to models assuming i.i.d. behavior within regimes.","kind":"predictive-accuracy","quote":"Our newly proposed model demonstrates superior out-of-sample predictive performance compared to existing models that assume i.i.d. behavior within each regime"},{"finding":"The MBOC model outperforms all competitors, including ARMA(1,1) and baseline BOCPD, in mean‑squared error forecasts of order flow.","kind":"performance","quote":"the baseline BOCPD model displays comparable performances"},{"finding":"Within a given regime, price dynamics exhibit a concave relationship with respect to time and volume, consistent with large‑order execution patterns.","kind":"statistical","quote":"Within a given regime, the price dynamics exhibit a concave relationship with respect to time and volume, mirroring the characteristics of actual large orders"},{"finding":"Incorporating regime information yields more accurate online predictions of order flow and market impact than models without regimes.","kind":"predictive-accuracy","quote":"By incorporating regime information, our model produces more accurate online predictions of order flow and market impact compared to models that do not consider regimes"},{"finding":"Regime‑switching methods outperform standard econometric time‑series models like ARMA(1,1) in forecasting order flow.","kind":"performance","quote":"In general, we find that the regime‑switching methods out‑perform standard econometric time series models like ARMA(1,1)"}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":32,"citations":{"cited_by_in_corpus":6,"by_independent_authors":5,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":2,"unclassified":4},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://gitlab.com/YvTsak/ScoreDrivenBOCPD","note":null},"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":"2026-11-14T18:25:05Z"},"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/"}