{"paper_id":"2409.12721","title":"Market Simulation under Adverse Selection","authors":["Luca Lalor","Anatoliy Swishchuk"],"paper_date":"2024-09-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2409.12721v2","page_url":"https://thequant.space/flowcharts/market-simulation-under-adverse-selection/","scores":{"empirical_rigor":6,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an enhanced simulation framework for evaluating HFT market‑making strategies that accounts for both adverse and non‑adverse trade order fills.","quote":"We propose an enhanced simulation framework for evaluating the performance of HFT strategies, particularly in market-making. This framework accounts for both adverse and non-adverse trade order fills in a more realistic manner","summary":"In this paper, we study the effects of fill probabilities and adverse fills on the trading strategy simulation process. We specifically focus on a stochastic optimal control market-making problem and test the strategy on ES (E-mini S&P 500), NQ (E-mini Nasdaq 100), CL (Crude Oil) and ZN (10-Year…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"For simplicity we assume that the fill probability ρ is constant over time (ρ∈(0,1)).","type":"model","stated":"explicit","quote":"for simplicity we assume that ρδ t = ρ with ρ ∈(0, 1)"},{"assumption":"Price data are resampled into 1‑second intervals using forward fill to handle irregular arrivals.","type":"data","stated":"explicit","quote":"We resampled our price data into a 1 second time interval, which was then subsequently used as the time step size in our discrete environment."},{"assumption":"Each market order is assumed to have a size of 1 in the simulation.","type":"model","stated":"explicit","quote":"we currently assume that each order has a size of 1"},{"assumption":"Adverse fills are guaranteed to occur based on LOB system rules.","type":"execution","stated":"explicit","quote":"adverse fills are guaranteed to occur based on the rules of most LOB systems"},{"assumption":"Non‑adverse fill probabilities are applied only to non‑adverse fills.","type":"execution","stated":"explicit","quote":"While fill probabilities are not new, they should only be applied to non‑adverse fills, as adverse fills are guaranteed to occur"}]},"datasets":{"status":"available","items":[{"name":"CME futures LOB data","provider":"CME","kind":"order-book","access":"commercial","period":"April 2024","universe":"ES, NQ, CL, ZN futures contracts","quote":"liquid U.S. futures contracts, calculated using LOB data from April 9, 2024"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"l2-book"},"transaction_costs":{"status":"not_extracted","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"none","rule":"R0","candidates":{"front_matter":"unclear","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the classifier was not confident"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The benchmark simulation environment inflates performance; the improved environment shows much worse results.","kind":"performance","quote":"the strategy performed reasonably well in the benchmark environment and much worse in our improved environment"},{"finding":"Excluding adverse fills and using unrealistic non‑adverse fill probabilities can significantly inflate strategy performance.","kind":"performance","quote":"excluding adverse fills and non‑adverse fill probabilities can significantly inflate the performance of a trading strategy"},{"finding":"Lower non‑adverse fill probabilities and the presence of adverse fills substantially affect wealth and inventory paths.","kind":"performance","quote":"have significantly affected how these processes evolved"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2407.16527","title":"The Negative Drift of a Limit Order Fill","paper_date":"2024-07-23","authors":["Timothy DeLise"],"empirical_rigor":4,"page_url":"https://thequant.space/flowcharts/the-negative-drift-of-a-limit-order-fill/"},"question":"How does the assumed fill probability impact observed strategy performance?","this_paper_finding":"Excluding adverse fills and using unrealistic non‑adverse fill probabilities can significantly inflate strategy performance.","other_paper_finding":"The empirical fill probability is much lower than the assumed 100% in many prior models.","other_paper_quote":"We will show later that we find this probability to be much lower than 1 in practice.","note":"Both note that using unrealistic 100% fill rates (A) inflates performance; B shows excluding adverse fills (non‑adverse probabilities) leads to over‑optimistic results, confirming A's lower empirical fill probability.","confidence":0.579}],"contradicts":[],"qualifies":[],"compared_with":11,"citations":{"cited_by_in_corpus":5,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":5},"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":"2026-11-14T18:01:45Z"},"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/"}