{"paper_id":"2502.04027","title":"High-Frequency Market Manipulation Detection with a Markov-modulated Hawkes process","authors":["Timothée Fabre","Ioane Muni Toke"],"paper_date":"2025-02-06","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.04027v1","page_url":"https://thequant.space/flowcharts/high-frequency-market-manipulation-detection-with-a-markov-m/","scores":{"empirical_rigor":7.5,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel self‑exciting point process with piecewise‑constant Hawkes intensity between events, estimated via an EM algorithm and a Viterbi procedure for state inference.","quote":"We introduce a novel self-exciting point process whose intensity is piecewise constant between event times, with a discretization step parameter δ.","summary":"This work focuses on a self-exciting point process defined by a Hawkes-like intensity and a switching mechanism based on a hidden Markov chain. Previous works in such a setting assume constant intensities between consecutive events. We extend the model to general Hawkes excitation kernels that are…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The underlying hidden Markov chain is M‑state, irreducible and aperiodic.","type":"model","stated":"explicit","quote":"parameters varying according to an unobservable M‑state irreducible and aperiodic continuous‑time Markov chain (St)t≥0."},{"assumption":"The Hawkes kernel in each state is non‑negative and decreasing.","type":"model","stated":"explicit","quote":"Inspired by Wang (2010), we develop an estimation procedure for such processes with a general non‑negative, decreasing kernel function."},{"assumption":"Intensity is piecewise constant between consecutive events (discretization step δ).","type":"model","stated":"explicit","quote":"We introduce a novel self‑exciting point process whose intensity is piecewise constant between event times, with a discretization step parameter δ."},{"assumption":"Trade timestamps have microsecond precision and reflect the matching‑engine processing time.","type":"data","stated":"explicit","quote":"With every trade comes a timestamp with microsecond precision. This timestamp corresponds to the time at which the matching engine of the market processed the transaction."},{"assumption":"Seasonality of trade intensity is removed by normalising over 5‑minute bins and using average daily patterns.","type":"data","stated":"explicit","quote":"over 5‑minutes bins each day. Then, we compute the average of these intensities per bin over the time period, with a 95% confidence interval."},{"assumption":"No trader identification numbers are available, so detection must rely on indirect methods.","type":"execution","stated":"explicit","quote":"traders’ IDs – even anonymous – are not provided by centralized venues, which makes wash trading detection extremely challenging."}]},"datasets":{"status":"available","items":[{"name":"SEI‑USD trades","provider":"Coinbase","kind":"crypto-onchain","access":"proprietary","period":"2023‑12‑01 to 2024‑03‑31","universe":"SEI token","quote":"The dataset is composed of trades executed for SEI‑USD between December 1st, 2023 and March 31st, 2024 on Coinbase.","known_id":"coinbase"}],"known":[],"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":"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":"unclear","findings":[{"finding":"The MMHP‑δ model provides a superior fit to the data compared with the Markov‑modulated Poisson process, as measured by AIC.","kind":"statistical","quote":"Firstly, the MMHP‑δ demonstrates a superior fit compared to the MMPP."},{"finding":"Reducing the discretization step δ improves the information‑criterion and goodness‑of‑fit, while larger δ worsens the QQ plots.","kind":"statistical","quote":"Additionally, for each regime configuration, a reduction in the discretization step δ appears to improve the criterion."},{"finding":"Calibration of the MMHP‑δ on a single day takes about 15 minutes with δ = 100 s and around ten hours with δ = 1 s.","kind":"other","quote":"As an example, for the estimation of the MMHP‑δ over a single day, the computation time is approximately 15 minutes with δ = 100s and around ten hours with δ = 1s."},{"finding":"The Viterbi‑derived state 3 trades are identified as natural candidates for suspicious wash‑trading activity.","kind":"performance","quote":"In our setting, trades classified in state 3 are natural candidates for suspicious trading activity."},{"finding":"Out‑of‑sample QQ plots show that MMHP‑δ with small δ (1 s or 10 s) outperforms the MMPP in goodness‑of‑fit.","kind":"statistical","quote":"We observe the MMHP‑δ with small δ (1 or 10) provides better results than the MMPP in terms of out‑of‑sample goodness‑of‑fit."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":47,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"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":"2026-11-14T17:45:54Z"},"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/"}