--- title: Derivatives & Volatility url: https://www.ml-quant.com/topics/derivatives-volatility/ site: ML-Quant (https://www.ml-quant.com) updated: 2026-10-09 license: Summaries CC BY 4.0; links go to the original sources index: https://www.ml-quant.com/llms.txt --- # Derivatives & Volatility Option pricing, volatility models and forecasting, hedging and implied surfaces. 883 papers featured; 53 in the last 12 months. Papers featured per quarter: 2023 Q2 34, 2023 Q3 119, 2023 Q4 99, 2024 Q1 130, 2024 Q2 100, 2024 Q3 101, 2024 Q4 47, 2025 Q1 81, 2025 Q2 92, 2025 Q3 27, 2025 Q4 25, 2026 Q1 1, 2026 Q2 2, 2026 Q3 10, 2026 Q4 15 ## Most cited - [Risk Revisited](https://www.ml-quant.com/papers/ssrn/4825844/): 88 citations. The study identifies recency, cluster, and sign as three factors shaping investors' risk perceptions of a stock, influencing trading volume and future volatility. - [Rough Volatility: Fact or Artefact?](https://www.ml-quant.com/papers/arxiv/2203.13820/): 54 citations. Fact or Artifact: The study proposes a new method to estimate the roughness of financial asset volatility, attributing observed roughness to microstructure noise. - [A Consolidated Volatility Prediction with Back Propagation Neural Network and Genetic Algorithm](https://www.ml-quant.com/papers/arxiv/2412.07223/): 25 citations. The article presents a unique AI model for predicting future volatility in emerging stock markets, showing high accuracy and low error rates. - [Physics-informed convolutional transformer for predicting volatility surface](https://www.ml-quant.com/papers/arxiv/2209.10771/): 24 citations. The paper presents a new architecture using physics-informed neural networks and convolutional transformers for better predicting financial market volatility. - [Rough PDEs for Local Stochastic Volatility Models](https://www.ml-quant.com/papers/arxiv/2307.09216/): 20 citations. The article presents a new way to set prices in local stochastic volatility models, using rough path theory to understand conditional dynamics and price European options. - [Robust Risk-Aware Option Hedging](https://www.ml-quant.com/papers/arxiv/2303.15216/): 19 citations. The study highlights the effectiveness of robust risk-aware reinforcement learning in managing risks related to path-dependent financial derivatives, especially in hedging barrier options, proving robust strategies are superior. - [Realised Volatility Forecasting: Machine Learning via Financial Word Embedding](https://www.ml-quant.com/papers/arxiv/2108.00480/): 18 citations. A new NLP framework shows that adding news text can improve stock volatility forecasting, particularly during volatile times, when combined with standard models. - [A path-dependent PDE solver based on signature kernels](https://www.ml-quant.com/papers/arxiv/2403.11738/): 18 citations. The article introduces a new, verifiably effective kernel-based solver for path-dependent partial differential equations (PPDEs). This provides a practical alternative to Monte Carlo methods, especially for option pricing under rough volatility. - [Convergence of Heavy-Tailed Hawkes Processes and the Microstructure of Rough Volatility](https://www.ml-quant.com/papers/arxiv/2312.08784/): 18 citations. The research identifies the weak convergence of a nearly-unstable Hawkes process with a heavy-tailed kernel, useful for creating a scaling limit for a financial market model. - [The Self-Organized Criticality Paradigm in Economics&Finance](https://www.ml-quant.com/papers/arxiv/2407.10284/): 17 citations. The article proposes Self-Organised Criticality as a reason for extreme volatility in financial markets and large business cycle fluctuations, calling for specific policy considerations. - [Operator Deep Smoothing for Implied Volatility](https://www.ml-quant.com/papers/arxiv/2406.11520/): 17 citations. A novel method for smoothing implied volatility using neural operators is presented, which maps data to smoothed surfaces, respects no-arbitrage rules, and is robust to input subsampling. - [First order Martingale model risk and semi-static hedging](https://www.ml-quant.com/papers/arxiv/2410.06906/): 16 citations. The study expands on previous research on model risk distributionally robust sensitivities, introducing the minimization of the distributionally robust problem in relation to semi-static hedging strategies and outlining the optimal strategies. ## Latest - [Beneath the VIX: Probability, Severity, and Uncertainty Shocks](https://www.ml-quant.com/papers/arxiv/2610.03849/) (2026-10-09): Separating risk-neutral shortfall probability from conditional severity in option prices shows that severity accounts for 91.5 percent of recession log premium movements, supplying joint empirical restrictions on uncertainty and economic activity. - [Adversarial Training for Deep Hedging in Nonstationary Markets](https://www.ml-quant.com/papers/arxiv/2610.07162/) (2026-10-09): WRAP combines Wasserstein reweighting and optimal-transport perturbations in a distributionally robust framework to make deep hedging policies robust to nonstationarity and distributional drift in market conditions. - [HAN-Mamba: Hierarchical Selective State Space Networks for Multi-Scale Financial Volatility Forecasting](https://www.ml-quant.com/papers/arxiv/2610.10323/) (2026-10-09): Replaces transformers with selective state space encoders in a hierarchical architecture for realized volatility forecasting, reducing error to 0.1927 on the Optiver benchmark with 33 percent fewer parameters than the attention variant. - [The Credit Spread at Long Horizons](https://www.ml-quant.com/papers/ssrn/7570200/) (2026-10-09): The study shows that Baa-Aaa spreads at 27-year maturity test pricing kernels better than shorter maturities, with a structural refinancing model matching observed spreads while prior kernels overpredict by 27 to 68 basis points. - [Delta-Guided Soft Actor-Critic for Derivative Hedgingunder Model Misspecification and Transaction Costs](https://www.ml-quant.com/papers/ssrn/7585078/) (2026-10-09): A reinforcement learning method embedding Black-Scholes delta guidance cuts hedging error by 19-38% across simulated and real options data with robust statistical significance. - [Volatility Disagreement in the Options Market](https://www.ml-quant.com/papers/repec/nbr-nberwo-35500/) (2026-10-09): Cross-sectional dispersion in volatility forecasts predicts delta-hedged straddle losses of 5.14% per month, consistent with mispricing rather than risk compensation. - [Negative Oil & Nickel Squeeze: A Feedback Model for Extreme Commodity Futures Prices](https://www.ml-quant.com/papers/arxiv/2610.00951/) (2026-10-02): A feedback model explains extreme commodity futures prices like negative oil by connecting delivery constraints to roll options and long-short position imbalances. - [When Hedging Changes the Payoff: Option Replication with Price Impact and Execution Costs](https://www.ml-quant.com/papers/arxiv/2609.36257/) (2026-10-02): The study shows how hedging a derivative via trading the underlying changes its payoff when execution generates price impact and costs, deriving pricing equations and replication conditions. - [Credit When it's Due: Corporate Bond Factors on a Schedule](https://www.ml-quant.com/papers/ssrn/7524680/) (2026-10-02): The research finds that the first five trading days of each month account for 73% of individual bond credit returns and 83% of the market credit premium, revealing a concentrated timing pattern in fixed-income compensation. - [Market-Implied Policy-Outcome Dispersion and Long-Run Equity Volatility: Meeting-Level Evidence from Kalshi FOMC Contracts](https://www.ml-quant.com/papers/ssrn/7531599/) (2026-10-02): Using Kalshi FOMC contract probabilities, the paper shows that cross-outcome variance in Federal Reserve policy expectations contains significant information about long-run stock market volatility. - [Tail Risk Hedging in Equity Portfolios: Evaluating the Cost-Effectiveness of Out-of-the-Money Put Options versus Dynamic Tail-Risk Mitigation Strategies During High-Volatility Regimes](https://www.ml-quant.com/papers/ssrn/7541959/) (2026-10-02): Static out-of-the-money put options provide crash protection but drag long-term returns, while dynamic tail-risk strategies adapt to market regimes and deliver superior risk-adjusted returns across cycles. - [Testing Whether Volatility Model Gains Persist: A Prespecified Holdout in Tail Risk Forecasting](https://www.ml-quant.com/papers/repec/cte-wsrepe-50798/) (2026-10-02): Testing eight volatility models on equity indices with prespecified holdout periods, the research finds that gains from more complex models often do not persist across markets or time. - [The implied volatility surface (also) is path-dependent](https://www.ml-quant.com/papers/repec/hal-journl-hal-04362544/) (2026-10-02): The research shows that past asset price trajectories predict implied volatility movements up to two years forward, with a parsimonious SSVI model capturing this path-dependent behavior. - [Diagnosing and Stabilizing Dynamic Correlations in Multivariate Stochastic Volatility Models](https://www.ml-quant.com/papers/repec/cte-wsrepe-50561/) (2026-10-02): Decomposing forecasting losses into correlation versus scale components, the paper shows how to diagnose and stabilize dynamic-correlation volatility models using realized-volatility inputs. - [Learn the measure, estimate the moment: machine-learned drivers in dynamic conditional correlation models](https://www.ml-quant.com/papers/repec/cdf-wpaper-2026-12/) (2026-10-02): Combining machine-learned forecasts of realized measures with dynamic conditional correlation models improves correlation matrix forecasts, producing valid predictions and beating realized-driver baselines across multiple horizons. - [Universal Diffusion Models for Implied Volatility Surfaces: Learning Shared Dynamics Across Stocks](https://www.ml-quant.com/papers/arxiv/2609.22893/) (2026-09-25): A 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 Dynamics](https://www.ml-quant.com/papers/arxiv/2609.27138/) (2026-09-25): Develops 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-Scholes](https://www.ml-quant.com/papers/arxiv/2609.27764/) (2026-09-25): Tree-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 pricing](https://www.ml-quant.com/papers/ssrn/7498639/) (2026-09-25): The 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 Sensitivity](https://www.ml-quant.com/papers/ssrn/7506360/) (2026-09-25): Leveraged 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 Distributions](https://www.ml-quant.com/papers/ssrn/7504480/) (2026-09-25): A 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 Calibration](https://www.ml-quant.com/papers/ssrn/7498326/) (2026-09-25): A 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 Forecasting](https://www.ml-quant.com/papers/repec/fip-fedgfe-103519/) (2026-09-25): Tree-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 Markets](https://www.ml-quant.com/papers/repec/ags-asea26-404810/) (2026-09-25): Financial 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 Forecasting](https://www.ml-quant.com/papers/repec/cdf-wpaper-2026-4/) (2026-09-25): Introducing 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 models](https://www.ml-quant.com/papers/arxiv/2604.00472/) (2026-04-03): The 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 Models](https://www.ml-quant.com/papers/arxiv/2511.02700/) (2026-04-03): The 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 Embedding](https://www.ml-quant.com/papers/arxiv/2108.00480/) (2026-01-16): A 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 Volatility](https://www.ml-quant.com/papers/ssrn/4482880/) (2025-12-28): The study shows that Ford Motor Company had its smallest earnings per share payout gap in 2020 compared to previous years. - [Global Liquidity and Volatility](https://www.ml-quant.com/papers/ssrn/4482265/) (2025-12-28): Global liquidity from banks impacts responses to crises and eases funding strains internationally.