{"paper_id":"2502.07071","title":"TRADES: Generating Realistic Market Simulations with Diffusion Models","authors":["Leonardo Berti","Bardh Prenkaj","Paola Velardi"],"paper_date":"2025-01-31","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.07071v3","page_url":"https://thequant.space/flowcharts/trades-generating-realistic-market-simulations-with-diffusi/","scores":{"empirical_rigor":7,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes TRADES, a Transformer-based Denoising Diffusion Probabilistic Engine for realistic and responsive LOB market simulations, and releases the DeepMarket framework and a synthetic LOB dataset.","quote":"We propose a novel TRAnsformer-based Denoising Diffusion Probabilistic Engine for LOB Simulations (TRADES).","summary":"Financial markets are complex systems characterized by high statistical noise, nonlinearity, volatility, and constant evolution. Thus, modeling them is extremely hard. Here, we address the task of generating realistic and responsive Limit Order Book (LOB) market simulations, which are fundamental…","strategy":null},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"LOB dataset from two NASDAQ stocks","provider":"NASDAQ","kind":"order-book","access":"public","period":"January 2nd to the 30th of 2015","universe":"Tesla and Intel","quote":"we create a LOB dataset from two NASDAQ stocks6 – i.e., Tesla and Intel – from January 2nd to the 30th of 2015."},{"name":"TRADES-LOB synthetic LOB dataset","provider":null,"kind":"synthetic","access":"public","period":null,"universe":"Tesla and Intel","quote":"TRADES-LOB comprises simulated TRADES market data for Tesla and Intel for two days."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"l2-book"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"TRADES outperforms the second‑best method by a factor of 3.27 on Tesla and 3.48 on Intel according to the predictive score (MAE).","kind":"performance","quote":"Usefulness: TRADES outperforms the second‑best by a factor of ×3.27 and ×3.48 on both stocks."},{"finding":"TRADES covers the real data distribution by 67% on average.","kind":"statistical","quote":"We showed that TRADES can cover the real data distribution by 67% on average"},{"finding":"Diffusion‑based simulations (TRADES) demonstrate substantial and permanent price impact when a POV agent is introduced, unlike market replay which shows only instantaneous impact.","kind":"performance","quote":"diffusion‑based simulations demonstrate substantial deviation from the baseline simulation without the POV agent, altering the price permanently."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":29,"citations":{"cited_by_in_corpus":4,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":3,"unclassified":1},"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":"2026-11-14T17:46:14Z"},"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/"}