{"paper_id":"2502.18625","title":"The Market Maker's Dilemma: Navigating the Fill Probability vs. Post-Fill Returns Trade-Off","authors":["Jakob Albers","Mihai Cucuringu","Sam Howison","Alexander Y. Shestopaloff"],"paper_date":"2025-02-25","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.18625v2","page_url":"https://thequant.space/flowcharts/the-market-makers-dilemma-navigating-the-fill-probability/","scores":{"empirical_rigor":8.5,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper develops a model to identify reversals where order‑book imbalance falsely predicts the next price change and uses it for a contrarian maker strategy.","quote":"we develop a model to identify when the order book imbalance falsely predicts the next price change. We term this a reversal","summary":"Using data from a live trading experiment on the Binance Bitcoin perpetual, we examine the effects of (i) basic order book mechanics and (ii) the persistence of price changes from immediate to short timescales, revealing the interplay between returns, queue sizes, and orders’ queue positions. We…","strategy":"Balanced-Inventory model-based market making (Logistic Regression)"},"assumptions":{"status":"available","items":[{"assumption":"The analysis assumes the best possible trading fees (maker rebate -0.5 bp, taker fee 1.5 bp).","type":"execution","stated":"explicit","quote":"In the subsequent analysis, we assume the best possible trading fees; naturally, any strategy results analyzed below would only deteriorate with less favorable fees."},{"assumption":"Tick size is negligible compared to fees.","type":"market","stated":"explicit","quote":"The tick size is 0.1 USD, or approximately 0.03 bp at the time of the experiment, which is negligible compared to fees."},{"assumption":"Orders with estimated fill probability above 80 % are selected for modeling.","type":"model","stated":"explicit","quote":"First, we extract the subset of orders with a high estimated fill probability, specifically those exceeding a chosen threshold of 80% at submission time"}]},"datasets":{"status":"available","items":[{"name":"O","provider":"Binance","kind":"order-book","access":"public","period":"2024-08-21 to 2024-08-31","universe":"Binance Bitcoin perpetual","quote":"This experiment ran from August 21 to 31, 2024, during which we submitted 172,800 minimum-sized maker orders","known_id":"binance"}],"known":[{"id":"binance","name":"Binance","provider":"Binance","kind":"market-prices","access":"public","quote":"2 Data Acquisition Our data was collected through live trading experiments carried out on Binance’s linear Bitcoin perpetual market, the most liquid crypto market globally.","mentions":9,"used_in":4}],"sample":{"start":null,"end":null,"market":"BTC perpetual futures","asset_class":"crypto","frequency":"intraday"},"data_resolution":"l2-book"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"Maker rebate -0.5 bp, taker fee 1.5 bp; best possible fees assumed in results.","quote":"the taker fee is 1.5 bp and the maker fee is −0.5 bp (i.e., a rebate for maker orders).","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Maker rebate -0.5 bp, taker fee 1.5 bp; best possible fees assumed in results.","card_quote":"the taker fee is 1.5 bp and the maker fee is −0.5 bp (i.e., a rebate for maker orders).","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"A negative correlation exists between maker fill likelihood and post‑fill returns.","kind":"negative","quote":"We document a fundamental trade-off: a negative correlation between maker fill likelihood and post-fill returns."},{"finding":"Out of 172,800 submitted minimum‑sized maker orders, 95,998 filled.","kind":"performance","quote":"we submitted 172,800 minimum-sized maker orders, of which 95,998 filled"},{"finding":"Logistic‑Regression reversal strategy at 0.24 threshold yields average return 0.71 bp and Sharpe 11.97, vastly outperforming the naive strategy (Sharpe –109).","kind":"performance","quote":"The Sharpe ratio improves from −109 for the naive strategy to 11.97 for the Logistic Regression-based strategy at the 0.24 threshold"},{"finding":"The reversal‑based strategy’s return improvement is statistically significant (t‑statistic 3.062602, p‑value 0.0011).","kind":"statistical","quote":"The calculated t-statistic is 3.062602 with a p-value of 0.0011, allowing us to reject the null hypothesis"}],"reported_performance":{"strategy":"Balanced-Inventory model-based market making (Logistic Regression)","sharpe":11.97,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":16,"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":"2026-11-14T17:44:39Z"},"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/"}