{"paper_id":"2307.13217","title":"Adversarial Deep Hedging: Learning to Hedge without Price Process Modeling","authors":["Masanori Hirano","Kentaro Minami","Kentaro Imajo"],"paper_date":"2023-07-25","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2307.13217v1","page_url":"https://thequant.space/flowcharts/adversarial-deep-hedging-learning-to-hedge-without-price-pr/","scores":{"empirical_rigor":6.5,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel adversarial deep hedging framework that learns a robust hedger without explicitly modeling the underlying asset price process.","quote":"In this study, we propose a new framework called adversarial deep hedging, inspired by adversarial learning.","summary":"Deep hedging is a deep-learning-based framework for derivative hedging in incomplete markets. The advantage of deep hedging lies in its ability to handle various realistic market conditions, such as market frictions, which are challenging to address within the traditional mathematical finance…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Discrete-time financial market with finite horizon and trading dates.","type":"market","stated":"explicit","quote":"We consider a discrete-time financial market with a finite time horizon"},{"assumption":"The underlying asset S is always tradable.","type":"market","stated":"explicit","quote":"is assumed to be always tradable, and its price at time"},{"assumption":"Proportional transaction cost charged at rate c per unit price.","type":"execution","stated":"explicit","quote":"a proportional transaction cost is charged at a rate of"},{"assumption":"Utility function u is used to define loss, examples include Entropic Risk Measure and CVaR.","type":"model","stated":"explicit","quote":"Expected Shortfall (Conditional Value at Risk; CVaR) is defined as"},{"assumption":"Generator determines the distribution parameters (μ, σ) of the next price S1 in the toy example.","type":"model","stated":"explicit","quote":"For simplicity, we assume that the distribution of"}]},"datasets":{"status":"available","items":[{"name":"S&P 500 data","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":"S&P 500 constituents","quote":"in the results on S&P 500 data, the Heston model tends to outperform other models."},{"name":"S&P 500 old data","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":"S&P 500 constituents (historical)","quote":"However, in the results on S&P500 old data, our proposed model tends to outperform other models."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Proportional transaction cost at rate c = 10⁻⁴ per unit price is included in the PL formulation.","quote":"a proportional transaction cost is charged at a rate of","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Proportional transaction cost at rate c = 10⁻⁴ per unit price is included in the PL formulation.","card_quote":"a proportional transaction cost is charged at a rate of","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"pricing-calibration","findings":[{"finding":"The proposed adversarial deep hedging model achieves competitive hedging performance, with differences to baselines typically less than 2%.","kind":"performance","quote":"While our proposed model does not consistently outperform the other baseline models, the differences between our model and others are relatively minor, typically less than 2%."},{"finding":"The proposed model obtains comparable performance to Brownian and Heston baselines across different utility functions and datasets.","kind":"performance","quote":"the proposed model achieves comparable performance to other models, regardless of the evaluation data or the utility function."},{"finding":"PL distributions of the proposed model replicate those of the Brownian model, especially when CVaR is used as the utility.","kind":"performance","quote":"According to these results, we can observe almost all of the PL distributions achieved by the Brownian model are replicated by our proposed adversarial deep hedging."},{"finding":"When ERM is used as utility, the proposed model generates positive PL with a positive probability, suggesting exploration of profit opportunities.","kind":"performance","quote":"Interestingly, it is apparent that when the utility function is ERM, the proposed model generates positive PL with a positive probability."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":31,"citations":{"cited_by_in_corpus":5,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":1,"mentions":1,"unclassified":3},"independent_papers":[{"paper":{"paper_id":"2503.04164","title":"CoFinDiff: Controllable Financial Diffusion Model for Time Series Generation","paper_date":"2025-03-06","authors":["Yuki Tanaka","Ryuji Hashimoto","Takehiro Takayanagi","Zhe Piao","Yuri Murayama","Kiyoshi Izumi"],"empirical_rigor":8.5,"page_url":"https://thequant.space/flowcharts/cofindiff-controllable-financial-diffusion-model-for-time-s/"},"how":"discusses_findings","quote":"Additionally, [CITED] employed deep generative models to learn unnecessary hedge strategies for asset price processes, achieving promising results though hedge performance did not necessarily improve."}],"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":"2026-11-14T18:24:08Z"},"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/"}