{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T12:34:51Z","timestamp":1792931691479,"version":"4.5.0"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":12,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.uspto.gov\/ip-policy\/copyright-policy\/copyright-basics"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>This paper introduces a rigorous, bounded semi-parametric framework for implied volatility surface modelling and dynamic hedging error minimisation, effectively resolving the structural instability and chronological out-of-sample breakdown inherent in unconstrained machine learning architectures. Conventional data-driven models frequently suffer from severe look-ahead bias and performance collapse under strict chronological evaluation due to unconstrained overfitting. To overcome these limitations, we propose a neural-gated volatility strategy that restricts predictive variations within the convex hull of robust structural baselines, constraining neural adjustments and exhibiting improved outof-sample forecast-error performance in the reported experiments. The architecture combines regimeadaptive parameterisations with bimodal shared-trunk mixture-of-experts routing governed by macroscopic volatility-of-volatility indicators, eliminating feature noise and gradient saturation during market transitions. Empirical evaluations across an extensive multi-year panel of index options demonstrate that the proposed framework consistently achieves superior variance reduction and temporal consistency compared to static and unconstrained benchmarks. Furthermore, theoretical and empirical analyses of optimisation dynamics reveal that controlled mini-batch discretisation provides essential implicit regularisation, illustrating a trade-off between forecast gains and adverse-month performance.<\/jats:p>","DOI":"10.2139\/ssrn.7651539","type":"posted-content","created":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T09:18:51Z","timestamp":1792660731000},"source":"Crossref","is-referenced-by-count":0,"title":["A Bounded Double-gated Framework for Implied-volatility Dynamics: Structural Anchoring and Regime-specialised Neural Learning"],"prefix":"10.2139","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8863-6607","authenticated-orcid":true,"given":"Daniel Alexandre","family":"Bloch","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ismayil","family":"Jafarov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"ref1","article-title":"Examining challenges in implied volatility forecasting: A critical review of data leakage and feature engineering combined with high-complexity models","author":"A Arratia","journal-title":"Computational Economics"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1086\/260062","article-title":"The pricing of options and corporate liabilities","volume":"81","author":"F Black","journal-title":"Journal of Political Economics"},{"key":"ref3","author":"D Bloch","journal-title":"Beyond the Greeks: Proactive neural hedging in turbulent markets. Working Paper, SSRN id 6641098"},{"key":"ref4","author":"D Bloch","journal-title":"Neural-Gated Multi-State Transition Frameworks for Semi-Parametric Convex Hedging. Working Paper, SSRN id 6863858"},{"key":"ref5","author":"J Cao","journal-title":"Neural network approach to understanding implied volatility movements"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1016\/j.orl.2023.05.007","article-title":"Data-driven hedging of stock index options via deep learning","volume":"51","author":"J Chen","journal-title":"Operations Research Letters"},{"key":"ref7","article-title":"Data-driven hedging with generative models","author":"R Cont","journal-title":"Annals of Operations Research"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.jbankfin.2017.05.006","article-title":"Optimal delta hedging for options","volume":"82","author":"J Hull","journal-title":"Journal of Banking and Finance"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/0304-405X(76)90022-2","article-title":"Option pricing when underlying stock returns are discontinuous","volume":"3","author":"R C Merton","journal-title":"Journal of Financial Economics"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.1080\/14697688.2017.1413245","article-title":"Learning minimum variance discrete hedging directly from the market","volume":"18","author":"K Nian","journal-title":"Quantitative Finance"},{"key":"ref11","article-title":"Learning sequential option hedging models from market data","volume":"133","author":"K Nian","journal-title":"Journal of Banking & Finance"},{"key":"ref12","author":"C Qiao","journal-title":"Enhancing Black-Scholes delta hedging via deep learning"}],"container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T11:39:57Z","timestamp":1792928397000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=7651539"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":12,"URL":"https:\/\/doi.org\/10.2139\/ssrn.7651539","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}