A two-step framework for arbitrage-free prediction of the implied volatility surface

DOI10.1080/14697688.2022.2135454zbMATH Open1518.91290arXiv2106.07177OpenAlexW3176125230MaRDI QIDQ6158370FDOQ6158370

Authors: Wenyong Zhang, Lingfei Li, Gongqiu Zhang 

Publication date: 20 June 2023

Published in: Quantitative Finance (Search for Journal in Brave)

Abstract: We propose a two-step framework for predicting the implied volatility surface over time without static arbitrage. In the first step, we select features to represent the surface and predict them over time. In the second step, we use the predicted features to construct the implied volatility surface using a deep neural network (DNN) model by incorporating constraints that prevent static arbitrage. We consider three methods to extract features from the implied volatility data: principal component analysis, variational autoencoder and sampling the surface, and we predict these features using LSTM. Using a long time series of implied volatility data for S&P500 index options to train our models, we find two feature construction methods, sampling the surface and variational autoencoders combined with DNN for surface construction, are the best performers in out-of-sample prediction. In particular, they outperform a classical method substantially. Furthermore, the DNN model for surface construction not only removes static arbitrage, but also significantly reduces the prediction error compared with a standard interpolation method. Our framework can also be used to simulate the dynamics of the implied volatility surface without static arbitrage.

Full work available at URL: https://arxiv.org/abs/2106.07177

Recommendations

• A neural network approach to understanding implied volatility movements
• Arbitrage-free smoothing of the implied volatility surface
• Short communication: Beyond surrogate modeling: learning the local volatility via shape constraints
• Arbitrage-free SVI volatility surfaces
• MODEL-FREE IMPLIED VOLATILITY: FROM SURFACE TO INDEX

zbMATH Keywords

predictiondeep learningimplied volatility surfacevariational autoencoderstatic arbitrage

Mathematics Subject Classification ID

Derivative securities (option pricing, hedging, etc.) (91G20) Artificial neural networks and deep learning (68T07)

Cites Work

• Title not available (Why is that?)
• Analytically tractable stochastic stock price models.
• Dynamics of implied volatility surfaces
• Semi-nonparametric estimation of the call-option price surface under strike and time-to-expiry no-arbitrage constraints
• Arbitrage-free smoothing of the implied volatility surface
• The dynamics of the S\&P 500 implied volatility surface
• Arbitrage-free SVI volatility surfaces
• Pricing under rough volatility
• The dynamics of implied volatilities: a common principal components approach
• A neural network approach to understanding implied volatility movements
• Universal features of price formation in financial markets: perspectives from deep learning
• Deep learning for limit order books
• Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models

Cited In (9)

• Data-driven hedging of stock index options via deep learning
• Simulation of Arbitrage-Free Implied Volatility Surfaces
• MODEL-FREE IMPLIED VOLATILITY: FROM SURFACE TO INDEX
• Arbitrage-Free Implied Volatility Surface Generation with Variational Autoencoders
• Arbitrage-free SVI volatility surfaces
• ON THE RELATIONSHIP BETWEEN THE CALL PRICE SURFACE AND THE IMPLIED VOLATILITY SURFACE CLOSE TO EXPIRY
• Model-free stochastic collocation for an arbitrage-free implied volatility. I.
• FuNVol: multi-asset implied volatility market simulator using functional principal components and neural SDEs
• Title not available (Why is that?)

This page was built for publication: A two-step framework for arbitrage-free prediction of the implied volatility surface

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6158370)