{"paper_id":"2502.13722","title":"Deep Learning for VWAP Execution in Crypto Markets: Beyond the Volume Curve","authors":["Remi Genet"],"paper_date":"2025-02-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.13722v2","page_url":"https://thequant.space/flowcharts/deep-learning-for-vwap-execution-in-crypto-markets-beyond-t/","scores":{"empirical_rigor":4,"math_complexity":6,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a deep learning framework that directly optimizes the VWAP execution objective, bypassing volume curve prediction.","quote":"I propose a deep learning framework that directly optimizes the VWAP execution objective by bypassing the intermediate step of volume curve prediction.","summary":"Volume-Weighted Average Price (VWAP) is arguably the most prevalent benchmark for trade execution as it provides an unbiased standard for comparing performance across market participants. However, achieving VWAP is inherently challenging due to its dependence on two dynamic factors, volumes and…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Market impact is negligible.","type":"market","stated":"explicit","quote":"One key assumption in the current framework is that market impact is negligible."},{"assumption":"The model operates in a static framework without dynamic updating.","type":"model","stated":"implied","quote":"Another limitation is that the present model operates in a static framework without dynamic updating in real time."}]},"datasets":{"status":"available","items":[{"name":"Binance perpetual futures contracts","provider":"Binance","kind":"market-prices","access":"public","period":"from contract inception until July 1, 20","universe":"BTC, ETH, ADA","quote":"Historical data from Binance perpetual futures contracts for Bitcoin (BTC), Ethereum (ETH), and Cardano (ADA) covering the period from contract inception until July 1, 2024","known_id":"binance"},{"name":"Hourly data from five major cryptocurrencies","provider":"Binance","kind":"market-prices","access":"public","period":"January 1, 2020 to July 1, 2024","universe":"BTC, ETH, BNB, ADA, XRP","quote":"The strategies are evaluated using hourly data from five major cryptocurrencies (BTC, ETH, BNB, ADA, and XRP) traded on Binance perpetual contracts covering the period from January 1, 2020, to July 1, 2024.","known_id":"binance"}],"known":[{"id":"binance","name":"Binance","provider":"Binance","kind":"market-prices","access":"public","quote":"4.1 Methodology Historical data from Binance perpetual futures contracts for Bitcoin (BTC), Ethereum (ETH), and Cardano (ADA) covering the period from contract inception until July 1, 2024, were employed.","mentions":2,"used_in":2}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":"One key assumption in the current framework is that market impact is negligible.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"One key assumption in the current framework is that market impact is negligible.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"execution-cost","findings":[{"finding":"Directly optimizing the VWAP execution objective consistently achieves lower VWAP slippage than conventional volume‑curve methods.","kind":"performance","quote":"My results demonstrate that this direct optimization approach consistently achieves lower VWAP slippage compared to conventional methods"},{"finding":"The performance gap between direct‑VWAP methods and volume‑prediction methods persists or widens with longer horizons.","kind":"performance","quote":"the performance gap between methods directly optimized for VWAP execution and those focused on volume prediction tends to persist or even widen with longer horizons"},{"finding":"The proposed method shows lower slippage during periods of high volatility.","kind":"performance","quote":"the proposed method generally exhibits lower slippage during periods of high volatility"},{"finding":"End‑loaded allocation strategies derived from direct VWAP optimization mitigate extreme slippage events.","kind":"performance","quote":"the prevalence of negative values during volatile periods provides strong visual evidence that the end-loaded allocation strategy is effective in mitigating execution slippage"},{"finding":"Direct VWAP optimization yields a strategy that deviates from simply mimicking the historical volume curve.","kind":"performance","quote":"These differences underscore that directly optimizing the VWAP objective (via absolute or quadratic loss) yields a strategy that deviates from simply mimicking the historical volume curve"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":33,"citations":{"cited_by_in_corpus":3,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":3},"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://github.com/remigenet/DeepLearningVWAP","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":"2026-11-14T17:45:05Z"},"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/"}