{"paper_id":"2502.18177","title":"Recurrent Neural Networks for Dynamic VWAP Execution: Adaptive Trading Strategies with Temporal Kolmogorov-Arnold Networks","authors":["Remi Genet"],"paper_date":"2025-02-25","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.18177v1","page_url":"https://thequant.space/flowcharts/recurrent-neural-networks-for-dynamic-vwap-execution-adapti/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a dynamic neural VWAP execution framework that integrates recurrent neural networks and a dynamic adjustment mechanism to continuously optimize execution decisions in real time.","quote":"We introduce two key innovations: first, the integration of recurrent neural networks to capture complex temporal dependencies in market dynamics, and second, a sophisticated dynamic adjustment mechanism that continuously optimizes execution decisions based on market feedback.","summary":"The execution of Volume Weighted Average Price (VWAP) orders remains a critical challenge in modern financial markets, particularly as trading volumes and market complexity continue to increase. In my previous work arXiv:2502.13722, I introduced a novel deep learning approach that demonstrated…","strategy":"Dynamic Neural VWAP Framework (dynamic TKAN/LSTM)"},"assumptions":{"status":"available","items":[{"assumption":"The framework assumes real‑time market feedback is available to adjust execution decisions.","type":"market","stated":"implied","quote":"a sophisticated dynamic adjustment mechanism that continuously optimizes execution decisions based on market feedback"},{"assumption":"The model uses a lookback window of 120 time steps to predict the next 12 periods, implying stationarity within that window.","type":"data","stated":"implied","quote":"The model processes market data using a lookback window of 120 time steps to generate predictions for the subsequent 12 periods."},{"assumption":"The approach does not explicitly model market impact in its execution cost calculations.","type":"execution","stated":"implied","quote":"while my framework achieves substantial improvements without explicitly modeling market impact"},{"assumption":"Future information does not affect current predictions due to causal padding in the architecture.","type":"model","stated":"implied","quote":"future information does not affect current predictions. The causality of the architecture guarantees that these padded values do not influence the predictions for the current timestep"}]},"datasets":{"status":"available","items":[{"name":"Hourly trading data from five major cryptocurrencies (BTC, ETH, BNB, ADA, XRP) on Binance ","provider":"Binance","kind":"crypto-onchain","access":"public","period":"inception of each contract until July 1,","universe":"BTC, ETH, BNB, ADA, XRP","quote":"The empirical analysis utilizes hourly trading data from five major cryptocurrencies (BTC, ETH, BNB, ADA, XRP) traded on Binance perpetual futures contracts. The dataset spans from the inception of each contract until July 1, 2024","known_id":"binance"}],"known":[{"id":"binance","name":"Binance","provider":"Binance","kind":"market-prices","access":"public","quote":"3.1 Experimental Setup 3.1.1 Dataset and Preprocessing The empirical analysis utilizes hourly trading data from five major cryptocurrencies (BTC, ETH, BNB, ADA, XRP) traded on Binance perpetual futures contracts.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":"BTC, ETH, BNB, ADA, XRP on Binance perpetual futures","asset_class":"crypto","frequency":"intraday"},"data_resolution":"intraday-bars"},"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":"execution-cost","findings":[{"finding":"The dynamic approach achieves execution performance gains of 10 to 15% in liquid markets.","kind":"performance","quote":"execution performance gains of 10 to 15% in liquid markets"},{"finding":"Dynamic‑VWAP with TKAN reduces absolute VWAP loss for ETH to 0.121, an 11.0% improvement over its static counterpart (0.136).","kind":"performance","quote":"For ETH, the DynamicVWAP with TKAN achieves an absolute VWAP loss of 0.121, an 11.0% improvement over its static counterpart (0.136)"},{"finding":"Training times increase by an order of magnitude (5‑8 s to >150 s) for TKAN implementations, with a 30% overhead for the dynamic framework justified by a 10‑15% execution quality improvement.","kind":"performance","quote":"When applied directly, RNNs introduce substantial computational overhead compared to simple linear models like TLN - training times increase by an order of magnitude, from 5-8 seconds to over 150 seconds for TKAN implementations. However, these architectures prove essential as building blocks for our dynamic framework."}],"reported_performance":{"strategy":"Dynamic Neural VWAP Framework (dynamic TKAN/LSTM)","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":24,"citations":{"cited_by_in_corpus":2,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":2},"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/DeepDynamicVWAP","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":"2026-11-14T17:44:35Z"},"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/"}