{"paper_id":"2408.12991","title":"Controllable Financial Market Generation with Diffusion Guided Meta Agent","authors":["Yu-Hao Huang","Chang Xu","Yang Liu","Weiqing Liu","Wu-Jun Li","Jiang Bian"],"paper_date":"2024-08-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2408.12991v3","page_url":"https://thequant.space/flowcharts/controllable-financial-market-generation-with-diffusion-guid/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes the Diffusion Guided Meta Agent (DigMA), a conditional diffusion model combined with a meta agent using financial economic priors to generate controllable order flow.","quote":"In this paper, we formulate the challenge of controllable financial market generation, and propose the Diffusion Guided Meta Agent (DigMA) model to address the challenge.","summary":"Generative modeling has transformed many fields, such as language and visual modeling, while its application in financial markets remains under-explored. As the minimal unit within a financial market is an order, order-flow modeling represents a fundamental generative financial task. However…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Wake‑up intervals of the meta agent follow an exponential distribution with rate λt supplied by the meta controller.","type":"model","stated":"explicit","quote":"the meta agent “wakes up” after a time interval δi drawn from an exponential distribution f(δi; λt) = λt e^{−λtδi}, where"},{"assumption":"The actor agent’s heterogeneous component weights (fundamental, chartist, noise) are drawn independently from exponential distributions with an expected ratio of 10:1.5:1.","type":"model","stated":"explicit","quote":"These weights are drawn independently from exponential distributions whose expected values follow a ratio of 10:1.5:1."},{"assumption":"The meta agent optimizes a CARA utility function based on current market observations to decide order demand.","type":"model","stated":"explicit","quote":"The agent makes decisions by optimizing a CARA utility function based on current market observations."},{"assumption":"The diffusion model is conditioned on three high‑level market indicators: return, amplitude, and volatility.","type":"model","stated":"explicit","quote":"we train DigMA using three indicators: return, amplitude, and volatility, each capturing a broad range of market conditions."},{"assumption":"Training and evaluation use real‑world tick‑by‑tick order‑flow data from two Chinese stock markets (A‑Main and ChiNext).","type":"data","stated":"explicit","quote":"We conduct experiments on two tick-by-tick order-flow datasets from global markets: A-Main and ChiNext from the Chinese stock market."},{"assumption":"During RL training, the agent receives a discrete action every 10 seconds and observes ten‑level bid‑ask price‑volume pairs and account information.","type":"execution","stated":"explicit","quote":"the agent takes a discrete action every 10… ten-level bid–ask price–volume pairs, and account information including capital, position, and cash."}]},"datasets":{"status":"available","items":[{"name":"A-Main","provider":null,"kind":"order-book","access":"unknown","period":null,"universe":null,"quote":"We conduct experiments on two tick-by-tick order-flow datasets from global markets: A-Main and ChiNext from the Chinese stock market."},{"name":"ChiNext","provider":null,"kind":"order-book","access":"unknown","period":null,"universe":null,"quote":"We conduct experiments on two tick-by-tick order-flow datasets from global markets: A-Main and ChiNext from the Chinese stock market."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"l2-book"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"DigMA achieves the lowest K‑L divergence on most stylized‑fact metrics, indicating superior fidelity in market simulation.","kind":"statistical","quote":"DigMA achieves the lowest K-L divergence on most metrics."},{"finding":"In the high‑frequency trading RL task, the agent trained in the DigMA‑generated environment attains the highest daily return (0.029%) and Sharpe ratio (0.049) among all baselines.","kind":"performance","quote":"The trading agent trained in the DigMA-generated environment achieves the highest daily return and Sharpe ratio among all baselines."},{"finding":"The DigMA‑c variant yields the lowest daily volatility (0.147) and maximum drawdown (0.715%), showing a more conservative strategy.","kind":"performance","quote":"agent trained with DigMA-c attains the lowest daily volatility and maximum drawdown."},{"finding":"DigMA is computationally efficient, requiring only 0.017 ms per order, faster than RFD (0.049 ms), RMSC (0.075 ms), and LOBGAN (1.710 ms).","kind":"performance","quote":"Model Time(ms)/Order RFD 0.049 RMSC 0.075 LOBGAN 1.710 DigMA 0.017"},{"finding":"The model can control generation to simulate order flow under target scenarios with high fidelity, as demonstrated by extensive experiments on real stock market data.","kind":"other","quote":"With DigMA, we are able to control the generation process to simulate order flow under target scenario with high fidelity."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"citations":{"cited_by_in_corpus":3,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":2,"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":"2026-11-14T18:03:31Z"},"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/"}