{"paper_id":"2312.05827","title":"Detecting Toxic Flow","authors":["Álvaro Cartea","Gerardo Duran-Martin","Leandro Sánchez-Betancourt"],"paper_date":"2023-12-10","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2312.05827v2","page_url":"https://thequant.space/flowcharts/detecting-toxic-flow/","scores":{"empirical_rigor":9,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel online Bayesian learning method called PULSE for training neural networks and a broker internalise‑externalise strategy based on toxicity predictions.","quote":"a novel online learning Bayesian method which we call the projection‑based unification of last‑layer and subspace estimation (PULSE).","summary":"This paper develops a framework to predict toxic trades that a broker receives from her clients. Toxic trades are predicted with a novel online learning Bayesian method which we call the projection-based unification of last-layer and subspace estimation (PULSE). PULSE is a fast and…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The broker quotes her clients the best available rates in LMAX Exchange net of fees.","type":"execution","stated":"explicit","quote":"we assume that the broker quotes her clients the best available rates in LMAX Exchange net of fees."},{"assumption":"Transaction costs in FX are around $3 per million euros traded, providing clients a discount of $3 per million euros.","type":"market","stated":"explicit","quote":"Transaction costs in FX are around $3 per million euros traded (see e.g., Cartea and Sánchez‑Betancourt (2023)), so this assumption provides clients with a discount of $3 per million euros traded when trading with the broker."},{"assumption":"Permanent price impact of externalising trades is ignored in the strategy evaluation.","type":"model","stated":"explicit","quote":"we ignore the permanent price impact of externalising trades, as this would require the formulation of a stochastic control problem."},{"assumption":"A trade is toxic if the client can unwind it at a profit within a given time window.","type":"other","stated":"explicit","quote":"In this paper, a trade is toxic over a given time window if the client can unwind the trade at a profit within the time window."},{"assumption":"The broker’s decision rule uses a cutoff probability p to internalise or externalise a trade.","type":"model","stated":"explicit","quote":"For a given toxicity horizon and a cutoff probability, the strategy internalises the trade if the probability that the trade is toxic is less than or equal to the cutoff probability, otherwise it externalises the trade."}]},"datasets":{"status":"available","items":[{"name":"Proprietary FX dataset (EUR/USD)","provider":"LMAX Broker / LMAX Exchange","kind":"market-prices","access":"proprietary","period":"28 June 2022 to 21 October 2022","universe":"EUR/USD currency pair","quote":"We employ data for the currency pair EUR/USD from LMAX Broker and from LMAX Exchange for the period 28 June 2022 to 21 October 2022."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"l2-book"},"transaction_costs":{"status":"available","modeled":"partial","headline_net_of_costs":null,"detail":"Assumes a flat $3 per million euros traded cost, providing a discount to clients; costs are not incorporated into the reported PnL results.","quote":"Transaction costs in FX are around $3 per million euros traded (see e.g., Cartea and Sánchez‑Betancourt (2023)), so this assumption provides clients with a discount of $3 per million euros traded when trading with the broker.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"partial","evidence_card_quoted":true},"card_detail":"Assumes a flat $3 per million euros traded cost, providing a discount to clients; costs are not incorporated into the reported PnL results.","card_quote":"Transaction costs in FX are around $3 per million euros traded (see e.g., Cartea and Sánchez‑Betancourt (2023)), so this assumption provides clients with a discount of $3 per million euros traded when trading with the broker.","meaning":"costs appear only as a robustness check, a flat fee without spread or impact, or outside the headline numbers"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"PULSE achieves the highest average AUC among all models for every toxicity horizon and outperforms benchmarks in profitability and loss avoidance.","kind":"performance","quote":"... the mean PnL of the internalise‑externalise strategy we obtain when training the MLP with PULSE is the highest (when compared with the benchmarks)."},{"finding":"A universal model trained on all traders yields higher toxicity prediction accuracy than models trained per individual trader.","kind":"predictive-accuracy","quote":"We obtain higher accuracies (when predicting toxic trades) when we train one model for all traders than when we train one model per trader; higher accuracies result from having more data."},{"finding":"Including client‑specific variables (identity and recent activity) improves PULSE performance substantially compared to a model without them.","kind":"performance","quote":"the performance of PULSE deteriorates substantially when compared to the performance of a model that includes the identity and unique features of the trader."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":12,"citations":{"cited_by_in_corpus":7,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":7},"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":"2026-11-14T18:17:56Z"},"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/"}