{"paper_id":"2503.17909","title":"Financial Wind Tunnel: A Retrieval-Augmented Market Simulator","authors":["Bokai Cao","Xueyuan Lin","Yiyan Qi","Chengjin Xu","Cehao Yang","Jian Guo"],"paper_date":"2025-03-23","paper_type":"software-tool","paper_url":"https://arxiv.org/pdf/2503.17909v1","page_url":"https://thequant.space/flowcharts/financial-wind-tunnel-a-retrieval-augmented-market-simulato/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a diffusion-based retrieval-augmented market simulator called Financial Wind Tunnel (FWT) that generates reliable, controllable and robust simulations across various data frequencies.","quote":"We propose a diffusion-based rtrieval-augmented market simulator, Financial Wind Tunnel (FWT), which generates reliable, controllable and robust simulation across vari- ous data frequencies.","summary":"Market simulator tries to create high-quality synthetic financial data that mimics real-world market dynamics, which is crucial for model development and robust assessment. Despite continuous advancements in simulation methodologies, market fluctuations vary in terms of scale and sources, but…","strategy":"Financial Wind Tunnel (FWT) enhanced transformer-based investment model"},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"CSI300 stocks","provider":"Shanghai and Shenzhen stock exchanges","kind":"market-prices","access":"public","period":"2010-2024","universe":"300 largest and most liquid Chinese stocks","quote":"CSI300 consists the 300 largest and most liquid stocks listed on the Shanghai and Shenzhen stock exchanges and is considered to be the most representative set of stock securities in China."},{"name":"Hong Kong Stock Exchange (HKSE) data","provider":"Hong Kong Stock Exchange","kind":"market-prices","access":"public","period":"aligned with CSI300 period (2010-2024)","universe":null,"quote":"In our cross-market study, we have utilize relevant data from the Hong Kong Stock Exchange (HKSE) with a aligned time period."},{"name":"FWT-generated synthetic data","provider":null,"kind":"synthetic","access":"proprietary","period":null,"universe":null,"quote":"We compare the model’s performance when trained solely on real market data versus when trained with additional FWT-generated synthetic data"}],"known":[],"sample":{"start":"2021-01","end":"2024-12","market":"CSI300 stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"tick"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The generated synthetic data improves downstream model performance, yielding higher annualized returns, reduced drawdowns, and an improved Sharpe ratio.","kind":"performance","quote":"This enhancement results in higher annualized returns, reduced drawdowns, and an improved Sharpe ratio."},{"finding":"Experimental results show that the approach enables generalizable and reliable market simulation, significantly improving performance and adaptability of downstream models in complex and volatile market conditions.","kind":"performance","quote":"Experimental results demonstrate that our approach enables the generalizable and reliable market simulation, significantly improve the performance and adaptability of downstream models, particularly in highly complex and volatile market conditions."},{"finding":"Increasing the amount of simulation data leads to significantly improved performance on unseen real market conditions.","kind":"performance","quote":"as the amount of simulation data increases, the model benefits from training in a more comprehensive and reasonable market environment, leading to significantly improved performance on unseen real market conditions."}],"reported_performance":{"strategy":"Financial Wind Tunnel (FWT) enhanced transformer-based investment model","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":2.2},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"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":"2026-11-14T17:41:57Z"},"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/"}