{"paper_id":"2609.33767","title":"Taming the Greeks: Option Portfolios with Inductive Biases","authors":["Wee Ling Tan","Stephen Roberts","Stefan Zohren"],"paper_date":"2026-09-27","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2609.33767","page_url":"https://thequant.space/flowcharts/taming-the-greeks-option-portfolios-with-inductive-biases/","scores":{"empirical_rigor":8,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an end-to-end deep learning framework that combines a performance-driven loss with a differentiable risk‑sensitivity penalty, introducing exposure‑normalized and Greek‑ratio drift penalty variants.","quote":"We propose a hybrid training objective L(θ) that combines a performance-driven objective with an explicit risk-sensitivity penalty.","summary":"We present an end-to-end deep learning framework for systematic options trading that directly embeds hedging behavior through explicit control of portfolio-level risk exposures. While neural networks trained to optimize risk-adjusted performance have been shown to outperform traditional rules-based…","strategy":"DP (L1) regularized model"},"assumptions":{"status":"available","items":[{"assumption":"Static delta‑neutral hedging is performed only at initiation with no subsequent adjustments.","type":"execution","stated":"explicit","quote":"This static hedging approach is consistent with [13, 15, 31], where a one-time delta hedge is implemented only at initiation, with no subsequent adjustments to the weights."},{"assumption":"Option Greeks and implied volatilities are computed using a binomial tree model (Cox‑Ross‑Rubinstein).","type":"model","stated":"explicit","quote":"The IVs and Greeks are calculated with a binomial tree model using Cox, Ross, and Rubinstein [8]."},{"assumption":"European‑style execution is assumed for near‑ATM options.","type":"market","stated":"explicit","quote":"This approach to computing returns inherently assumes European-style execution, given our focus on near-ATM options that retain substantial extrinsic value."},{"assumption":"Transaction costs are proportional to daily turnover measured in basis points.","type":"other","stated":"explicit","quote":"where c denotes the proportional cost per unit of turnover, expressed in basis points."},{"assumption":"Liquidity is sufficient; the dataset comprises deep and liquid options markets for Nasdaq‑100 constituents.","type":"market","stated":"explicit","quote":"This universe comprises a broad cross-section of large-cap US equities and are characterized by relatively deep and liquid options markets."}]},"datasets":{"status":"available","items":[{"name":"OptionMetrics Ivy DB","provider":"OptionMetrics","kind":"options","access":"commercial","period":"January 2010 to December 2023","universe":"Nasdaq 100 Index constituents","quote":"... we restrict our analysis to the universe of option contracts written on constituents of the Nasdaq 100 Index over the period from January 2010 to December 2023.","known_id":"optionmetrics"}],"known":[{"id":"optionmetrics","name":"OptionMetrics IvyDB","provider":"OptionMetrics","kind":"options","access":"commercial","quote":"Tan, S. Roberts, S. Zohren Option Portfolios with Inductive Biases 3 Dataset Description We obtain our equity option dataset from the OptionMetrics Ivy DB database.","mentions":2,"used_in":1}],"sample":{"start":null,"end":null,"market":"Nasdaq 100 equity options","asset_class":"options","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"Costs are incorporated as a proportional fee c (in basis points) applied to daily turnover in the turnover‑adjusted return calculation.","quote":"where c denotes the proportional cost per unit of turnover, expressed in basis points.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Costs are incorporated as a proportional fee c (in basis points) applied to daily turnover in the turnover‑adjusted return calculation.","card_quote":"where c denotes the proportional cost per unit of turnover, expressed in basis points.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Regularized models improve out‑of‑sample risk‑adjusted performance relative to an unregularized baseline while reducing realized directional exposure.","kind":"performance","quote":"appropriately calibrated models not only exhibit competitive out-of-sample hedging performance but also simultaneously improve risk-adjusted returns relative to an unregularized baseline."},{"finding":"DP (L1) achieves the highest Sharpe ratio of 2.339 at zero transaction cost, outperforming all other variants.","kind":"performance","quote":"DP (L1) achieving the highest Sharpe ratio of 2.339."},{"finding":"At high transaction costs (100 bps), the baseline LSTM with turnover regularization attains the top Sharpe (0.871), slightly ahead of DP (L1) at 0.860.","kind":"performance","quote":"At the highest cost level of 100 bps, Baseline LSTM + TC Reg achieves the highest Sharpe ratio of 0.871, followed closely by DP (L1) at 0.860."},{"finding":"ENP (L2) retains a Sharpe ratio above 2.0 across regularization strengths α = 100‑104 while reducing median net Delta to 0.072.","kind":"performance","quote":"ENP (L2), in particular, retains a Sharpe ratio above 2.0 across α = 100 through 104, while eventually reducing the median net Delta to 0.072."},{"finding":"Increasing regularization beyond moderate levels sharply deteriorates performance as the model’s capacity to generate signals is suppressed.","kind":"negative","quote":"The deterioration in performance observed at extreme values of α confirms that hedging is not costless: once the risk-sensitivity penalty is given overwhelming weight, the model’s capacity to generate meaningful trading signals is suppressed."}],"reported_performance":{"strategy":"DP (L1) regularized model","sharpe":2.339,"sharpe_benchmark":0.621,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":21},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":57,"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":"2026-11-14T17:04:35Z"},"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/"}