{"paper_id":"2409.13567","title":"Deep Gamma Hedging","authors":["John Armstrong","George Tatlow"],"paper_date":"2024-09-20","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2409.13567v1","page_url":"https://thequant.space/flowcharts/deep-gamma-hedging/","scores":{"empirical_rigor":4.5,"math_complexity":7.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes using neural networks to learn optimal replication strategies that implement gamma hedging with two instruments, the underlying and a hedging option.","quote":"We train neural networks to learn optimal replication strategies for an option when two replicating instruments are available, namely the underlying and a hedging option.","summary":"We train neural networks to learn optimal replication strategies for an option when two replicating instruments are available, namely the underlying and a hedging option. If the price of the hedging option matches that of the Black–Scholes model then we find the network will successfully learn the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Option prices are given by the Black‑Scholes formula with a fixed volatility σ.","type":"model","stated":"explicit","quote":"We will assume that at all times t ∈[0, T ′] the price of the option with strike Kα is given by the Black‑Scholes formula Vαt = BS(St, Kα, r, T −t, σ)."},{"assumption":"The underlying follows dSt = St(µη dt + ση dWt) with random parameters µη, ση and random initial condition Sη.","type":"market","stated":"explicit","quote":"where µη and ση are random parameter values and Sη is a random initial condition."},{"assumption":"Proportional transaction costs pα are incurred when purchasing each derivative.","type":"execution","stated":"explicit","quote":"We will assume that there are proportional transaction costs pα given when purchasing the derivative α."},{"assumption":"All derivative contracts are European options with smooth payoff functions at maturity.","type":"model","stated":"explicit","quote":"we want the gamma of all these derivative contracts to be finite on the whole of [0, T ′]. To achieve this we will assume that the derivative contracts are all European options with smooth payoff functions at time T ′."},{"assumption":"Trading occurs at evenly spaced discrete time points {0, δt, 2δt, …, (n‑1)δt} with nδt = T′.","type":"execution","stated":"explicit","quote":"The trader will only trade at evenly spaced discrete time points {0, δt, 2δt, . . . , (n −1)δt} where nδt = T ′."},{"assumption":"The payoff functions at time T′ are given by the Black‑Scholes formula for call options with maturity T > T′.","type":"model","stated":"explicit","quote":"convenience we will further assume that the payoff functions at time T ′ are given by the Black‑Scholes formula for the price of call options with maturity at time T, where T > T ′."}]},"datasets":{"status":"available","items":[{"name":"Synthetic market data based on S&P 500 parameters","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"Our volatility values and our proportional transaction cost values in section 4.3 are based on market data for the S&P 500."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Proportional costs p1 and p2 are set to 0.0 % (no cost), 0.005 %/0.25 % (normal) and 0.5 %/0.5 % (high) per trade.","quote":"We evaluate the performance of this network under three different sets of proportional transaction costs: no transaction costs (p1 = p2 = 0.0%); normal transaction costs (p1 = 0.005%, p2 = 0.25%) based on market data for the S&P 500; and high transaction costs (p1 = p2 = 0.5%).","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Proportional costs p1 and p2 are set to 0.0 % (no cost), 0.005 %/0.25 % (normal) and 0.5 %/0.5 % (high) per trade.","card_quote":"We evaluate the performance of this network under three different sets of proportional transaction costs: no transaction costs (p1 = p2 = 0.0%); normal transaction costs (p1 = 0.005%, p2 = 0.25%) based on market data for the S&P 500; and high transaction costs (p1 = p2 = 0.5%).","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"When the hedging option price matches Black‑Scholes, the network learns the Black‑Scholes gamma‑hedging strategy even if the underlying dynamics differ, provided the loss rewards coping with model uncertainty.","kind":"theoretical","quote":"If the price of the hedging option matches that of the Black–Scholes model then we find the network will successfully learn the Black‑Scholes gamma hedging strategy, even if the dynamics of the underlying do not match the Black‑Scholes model, so long as we choose a loss function that rewards coping with model uncertain"},{"finding":"Deep‑hedging strategies using both the underlying and an option outperform those using only the underlying, both with known dynamics and under model uncertainty.","kind":"performance","quote":"an option markedly outperform strategies which only use the underlying."},{"finding":"As the hedging interval shrinks, the robust optimal strategy converges to the gamma‑hedging strategy.","kind":"theoretical","quote":"as we increase the values of n and thus δt →0, the optimal robust hedging strategy tends to the gamma‑hedging strategy."},{"finding":"When transaction costs are introduced, blindly following gamma hedging becomes suboptimal; deep‑learning discovers a nuanced adaptation that substantially outperforms other strategies.","kind":"performance","quote":"Whilst gamma hedging can offer an improved performance to delta hedging when focusing on robust hedging, once transaction costs are introduce, blindly gamma hedging is suboptimal. Deep‑learning can identify a more nuanced adaptation of gamma‑hedging which substantially outperforms the other strategies."},{"finding":"Gamma hedging is more valuable for coping with model uncertainty than for reducing transaction costs.","kind":"theoretical","quote":"Together, these results suggest that in practice gamma hedging is more valuable for its ability to cope with model uncertainty than for reducing transaction costs."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":31,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"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":"2026-11-14T18:02:04Z"},"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/"}