ML-Quant: Derivatives & Volatilityhttps://www.ml-quant.com/topics/derivatives-volatility/Option pricing, volatility models and forecasting, hedging and implied surfaces. en Universal Diffusion Models for Implied Volatility Surfaces: Learning Shared Dynamics Across Stockshttps://www.ml-quant.com/papers/arxiv/2609.22893/https://www.ml-quant.com/papers/arxiv/2609.22893/Fri, 25 Sep 2026 07:00:00 +0000A universal diffusion model trained on pooled data from 50 stocks learns to jointly generate implied volatility surface changes and stock returns, extrapolating well to unseen stocks. Surface-Driven Stochastic Volatility for Commodity Options: Identification of Stochastic Vol-of-Vol and Leverage from Smile Dynamicshttps://www.ml-quant.com/papers/arxiv/2609.27138/https://www.ml-quant.com/papers/arxiv/2609.27138/Fri, 25 Sep 2026 07:00:00 +0000Develops a surface-driven stochastic volatility framework for commodity options using daily volatility surface factors, recovering vol-of-vol and leverage parameters from smile dynamics. Learning to Detect Symbolic Failure: Machine Learning and the Limits of Black-Scholeshttps://www.ml-quant.com/papers/arxiv/2609.27764/https://www.ml-quant.com/papers/arxiv/2609.27764/Fri, 25 Sep 2026 07:00:00 +0000Tree-based machine learning outperforms neural networks at detecting systematic option-pricing deviations from Black-Scholes using 2.6 million real contracts, with domain-expert features crucial. Prices or implied volatilities? Choosing the loss function in machine learning option pricinghttps://www.ml-quant.com/papers/ssrn/7498639/https://www.ml-quant.com/papers/ssrn/7498639/Fri, 25 Sep 2026 07:00:00 +0000The paper compares machine learning option pricing trained on pricing errors versus implied-volatility errors using 8.67 million S&P 500 index-option observations from 1997 through 2025. Hedge Fund Trading and Sovereign Bond Yield Sensitivityhttps://www.ml-quant.com/papers/ssrn/7506360/https://www.ml-quant.com/papers/ssrn/7506360/Fri, 25 Sep 2026 07:00:00 +0000Leveraged hedge fund positions amplify sovereign bond yield sensitivity to monetary shocks by over a quarter through directional rebalancing, with effects scaling to position intensity. Tail-Risk Forecasting with General Cubic Distributionshttps://www.ml-quant.com/papers/ssrn/7504480/https://www.ml-quant.com/papers/ssrn/7504480/Fri, 25 Sep 2026 07:00:00 +0000A cubic quantile framework forecasts Value-at-Risk and Expected Shortfall more reliably than GARCH benchmarks across eight equity indices without requiring a parametric density. MartingaleONet: Physics-Constrained Operator Learning for Real-Time Option Pricing and Volatility Calibrationhttps://www.ml-quant.com/papers/ssrn/7498326/https://www.ml-quant.com/papers/ssrn/7498326/Fri, 25 Sep 2026 07:00:00 +0000A deep operator network maps volatility surfaces to option prices under the Heston model 15,000 times faster than finite-difference methods while reducing dynamic hedging variance by over 59% under transaction costs. Capturing Heterogeneity: Machine Learning Approaches to Implied Volatility Forecastinghttps://www.ml-quant.com/papers/repec/fip-fedgfe-103519/https://www.ml-quant.com/papers/repec/fip-fedgfe-103519/Fri, 25 Sep 2026 07:00:00 +0000Tree-based models partition the option surface by moneyness and maturity to forecast volatility, reducing one-month-ahead errors by 13 percent versus benchmark models. How Economic News Drives Implied Volatility in Agricultural Commodity Marketshttps://www.ml-quant.com/papers/repec/ags-asea26-404810/https://www.ml-quant.com/papers/repec/ags-asea26-404810/Fri, 25 Sep 2026 07:00:00 +0000Financial and macroeconomic news topics systematically predict implied volatility in corn and soybean markets, with program trading and 2008 crisis topics most robust at short horizons. Adaptive LASSO-MGARCH for Multivariate Volatility Forecastinghttps://www.ml-quant.com/papers/repec/cdf-wpaper-2026-4/https://www.ml-quant.com/papers/repec/cdf-wpaper-2026-4/Fri, 25 Sep 2026 07:00:00 +0000Introducing coefficient-specific penalization into multivariate GARCH equations reduces complexity and improves out-of-sample covariance forecasts across bonds, equities, and commodities. Valuation of variable annuities under the Volterra mortality and rough Heston modelshttps://www.ml-quant.com/papers/arxiv/2604.00472/https://www.ml-quant.com/papers/arxiv/2604.00472/Fri, 03 Apr 2026 07:00:00 +0000The paper discusses how to value variable annuity contracts that offer early surrender options. It uses advanced models and deep learning to find the best strategies for surrendering the contracts, while also providing protection against losses through minimum benefits. Numerical valuation of European options under two-asset infinite-activity exponential Lévy modelshttps://www.ml-quant.com/papers/arxiv/2511.02700/https://www.ml-quant.com/papers/arxiv/2511.02700/Fri, 03 Apr 2026 07:00:00 +0000The article introduces a better method for pricing European-style options using two-asset exponential Lévy models. It focuses on faster calculations by employing fast Fourier transforms and a semi-Lagrangian approach, surpassing older techniques. Realised Volatility Forecasting: Machine Learning via Financial Word Embeddinghttps://www.ml-quant.com/papers/arxiv/2108.00480/https://www.ml-quant.com/papers/arxiv/2108.00480/Fri, 16 Jan 2026 07:00:00 +0000A new NLP framework shows that adding news text can improve stock volatility forecasting, particularly during volatile times, when combined with standard models. Analysis of Fundamental and Technical Financial Ford Motor Company with The Arrangements of Implication Black Volatilityhttps://www.ml-quant.com/papers/ssrn/4482880/https://www.ml-quant.com/papers/ssrn/4482880/Sun, 28 Dec 2025 07:00:00 +0000The study shows that Ford Motor Company had its smallest earnings per share payout gap in 2020 compared to previous years. Global Liquidity and Volatilityhttps://www.ml-quant.com/papers/ssrn/4482265/https://www.ml-quant.com/papers/ssrn/4482265/Sun, 28 Dec 2025 07:00:00 +0000Global liquidity from banks impacts responses to crises and eases funding strains internationally. Robert C. Merton's Contributionshttps://www.ml-quant.com/papers/ssrn/4480625/https://www.ml-quant.com/papers/ssrn/4480625/Sun, 28 Dec 2025 07:00:00 +0000Robert C. Merton is a significant finance scholar known for his work on derivatives pricing and finance theories. Low Volatility Asset Valuation in Brazilian Stock Market: Lower Risk with Higher Returnshttps://www.ml-quant.com/papers/ssrn/4480285/https://www.ml-quant.com/papers/ssrn/4480285/Sun, 28 Dec 2025 07:00:00 +0000Lower volatility Brazilian stocks have consistently outperformed high-volatility stocks in annual returns from 2003 to 2021. Global Dollar Holdings Trendshttps://www.ml-quant.com/papers/ssrn/4478513/https://www.ml-quant.com/papers/ssrn/4478513/Sun, 28 Dec 2025 07:00:00 +0000Foreign institutional investors significantly increased their USD security holdings, influenced by varying currency hedging demands. Asymptotic Expansions for High-Frequency Option Datahttps://www.ml-quant.com/papers/ssrn/4440168/https://www.ml-quant.com/papers/ssrn/4440168/Fri, 19 Dec 2025 07:00:00 +0000A new method for analyzing financial data helps test for sudden volatility changes, with evidence from SP500 options indicating significant variation. Deep Hedging with Reinforcement Learning: A Practical Framework for Option Risk Managementhttps://www.ml-quant.com/papers/arxiv/2512.12420/https://www.ml-quant.com/papers/arxiv/2512.12420/Fri, 19 Dec 2025 07:00:00 +0000The article describes a reinforcement-learning method for hedging equity index options that enhances risk-adjusted returns while managing turnover and costs. An Efficient Machine Learning Framework for Option Pricing via Fourier Transformhttps://www.ml-quant.com/papers/arxiv/2512.16115/https://www.ml-quant.com/papers/arxiv/2512.16115/Fri, 19 Dec 2025 07:00:00 +0000A new algorithmic framework merges a smooth offset method with machine learning for quicker pricing of path-independent options, vastly speeding up evaluations compared to older techniques. Stochastic Volatility Modelling with LSTM Networks: A Hybrid Approach for S&P 500 Index Volatility Forecastinghttps://www.ml-quant.com/papers/arxiv/2512.12250/https://www.ml-quant.com/papers/arxiv/2512.12250/Fri, 19 Dec 2025 07:00:00 +0000A combined model of Stochastic Volatility and Long Short Term Memory networks offers better volatility predictions for the S&P 500, outperforming traditional models for improved risk assessment. Option-Implied Zero-Coupon Yields: Unifying Bond and Equity Marketshttps://www.ml-quant.com/papers/arxiv/2512.10823/https://www.ml-quant.com/papers/arxiv/2512.10823/Sun, 14 Dec 2025 07:00:00 +0000The paper presents a new approach to pricing zero-coupon bonds that aligns them with equity options for more accurate interest rate modeling. DeepSVM: Learning Stochastic Volatility Models with Physics-Informed Deep Operator Networkshttps://www.ml-quant.com/papers/arxiv/2512.07162/https://www.ml-quant.com/papers/arxiv/2512.07162/Sun, 14 Dec 2025 07:00:00 +0000Physics-Informed Volatility: DeepSVM is a machine learning model that accurately calibrates stochastic volatility without labels, but needs better regularization for derivatives. CREDIT DERIVATIVE -An Alternative Tool for Indian Commercial Banks to Transfer Credit Riskhttps://www.ml-quant.com/papers/ssrn/4973692/https://www.ml-quant.com/papers/ssrn/4973692/Mon, 01 Dec 2025 07:00:00 +0000Poor credit risk management in Indian banks has led to rising Non-Performing Assets, highlighting the need for modern risk tools, such as credit derivatives, to improve future performance. European Real Estate Volatilityhttps://www.ml-quant.com/papers/ssrn/4964818/https://www.ml-quant.com/papers/ssrn/4964818/Mon, 01 Dec 2025 07:00:00 +0000This study shows that different European real estate markets have varying volatility and suggests using tactical asset allocation to improve investment performance. Constrained deep learning for pricing and hedging european options in incomplete marketshttps://www.ml-quant.com/papers/arxiv/2511.20837/https://www.ml-quant.com/papers/arxiv/2511.20837/Mon, 01 Dec 2025 07:00:00 +0000This article discusses a method using deep learning to price and hedge European options in incomplete markets, optimizing risk distribution while handling tricky payoffs. Signature approach for pricing and hedging path-dependent options with frictionshttps://www.ml-quant.com/papers/arxiv/2511.23295/https://www.ml-quant.com/papers/arxiv/2511.23295/Mon, 01 Dec 2025 07:00:00 +0000This innovative approach simplifies the pricing and hedging of path-dependent options, improving strategies in markets with friction through numerical analysis. Beta-Dependent Gamma Feedback and Endogenous Volatility Amplification in Option Marketshttps://www.ml-quant.com/papers/arxiv/2511.22766/https://www.ml-quant.com/papers/arxiv/2511.22766/Mon, 01 Dec 2025 07:00:00 +0000The study connects individual option hedging to broader market volatility, revealing how market-maker actions during volatility spikes can increase fluctuations, especially in low-beta stocks. Empirical examination of the stability of expectations -Augmented Phillips Curve for developing and developed countrieshttps://www.ml-quant.com/papers/arxiv/2511.22786/https://www.ml-quant.com/papers/arxiv/2511.22786/Mon, 01 Dec 2025 07:00:00 +0000The research on the Phillips Curve from 1980 to 2016 reveals strong forward-looking inflation expectations in developed countries, while others face challenges in its application due to past volatility.