Machine learning for pricing American options in high-dimensional Markovian and non-Markovian models
From MaRDI portal
Abstract: In this paper we propose two efficient techniques which allow one to compute the price of American basket options. In particular, we consider a basket of assets that follow a multi-dimensional Black-Scholes dynamics. The proposed techniques, called GPR Tree (GRP-Tree) and GPR Exact Integration (GPR-EI), are both based on Machine Learning, exploited together with binomial trees or with a closed formula for integration. Moreover, these two methods solve the backward dynamic programming problem considering a Bermudan approximation of the American option. On the exercise dates, the value of the option is first computed as the maximum between the exercise value and the continuation value and then approximated by means of Gaussian Process Regression. The two methods mainly differ in the approach used to compute the continuation value: a single step of binomial tree or integration according to the probability density of the process. Numerical results show that these two methods are accurate and reliable in handling American options on very large baskets of assets. Moreover we also consider the rough Bergomi model, which provides stochastic volatility with memory. Despite this model is only bidimensional, the whole history of the process impacts on the price, and handling all this information is not obvious at all. To this aim, we present how to adapt the GPR-Tree and GPR-EI methods and we focus on pricing American options in this non-Markovian framework.
Recommendations
Cites work
- A lattice approach for pricing of multivariate contingent claims
- American options by Malliavin calculus and nonparametric variance and bias reduction methods
- Application of data clustering and machine learning in variable annuity valuation
- Asymptotic analysis of the learning curve for Gaussian process regression
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Deep optimal stopping
- Discrete-time approximation and Monte-Carlo simulation of backward stochastic differential equations
- Dual pricing of American options by Wiener chaos expansion
- First-Order Schemes in the Numerical Quantization Method
- Gaussian processes for machine learning.
- High order discretization schemes for the CIR process: application to affine term structure and heston models
- Machine learning for quantitative finance: fast derivative pricing, hedging and fitting
- Monte Carlo valuation of American options
- Optimal stopping of Markov processes: Hilbert space theory, approximation algorithms, and an application to pricing high-dimensional financial derivatives
- Pricing American Options: A Duality Approach
- Pricing American-style securities using simulation
- Pricing and hedging American options by Monte Carlo methods using a Malliavin calculus approach
- Pricing and hedging GMWB in the Heston and in the Black-Scholes with stochastic interest rate models
- Pricing high-dimensional Bermudan options using the stochastic grid method
- Pricing of high-dimensional American options by neural networks
- Pricing under rough volatility
- Solving high-dimensional partial differential equations using deep learning
- Stochastic processes and applications. Diffusion processes, the Fokker-Planck and Langevin equations
- Valuation of large variable annuity portfolios under nested simulation: a functional data approach
- Valuing American options by simulation: a simple least-squares approach
Cited in
(33)- Gaussian process regression for pricing variable annuities with stochastic volatility and interest rate
- DNN expression rate analysis of high-dimensional PDEs: application to option pricing
- Computational analysis of the behavior of stochastic volatility models with financial applications
- Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
- Moving average options: machine learning and Gauss-Hermite quadrature for a double non-Markovian problem
- Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities
- Machine learning for quantitative finance: fast derivative pricing, hedging and fitting
- Deep splitting method for parabolic PDEs
- Pricing options under rough volatility with backward SPDEs
- Short-dated smile under rough volatility: asymptotics and numerics
- JDOI variance reduction method and the pricing of American-style options
- American options in the Volterra Heston model
- Krighedge: Gaussian process surrogates for delta hedging
- Numerical simulations for full history recursive multilevel Picard approximations for systems of high-dimensional partial differential equations
- Implied stopping rules for American basket options from Markovian projection
- Generative Bayesian neural network model for risk-neutral pricing of American index options
- A deep-genetic algorithm (deep-GA) approach for high-dimensional nonlinear parabolic partial differential equations
- Local volatility under rough volatility
- Applications of artificial neural networks to simulating Lévy processes
- Monte Carlo method for pricing lookback type options in Lévy models
- Fast calculation of integral convolution operators in problems of evaluating options in Lévy's models
- An overview of approximate dynamic programming methods for optimal stopping problems
- Purely dual approach for optimal stopping problems via regression
- A deep learning-based Monte Carlo algorithm with applications in American options pricing
- Computing XVA for American basket derivatives by machine learning techniques
- Space-time deep neural network approximations for high-dimensional partial differential equations
- Primal and dual optimal stopping with signatures
- Simultaneous upper and lower bounds of American-style option prices with hedging via neural networks
- A general valuation framework for rough stochastic local volatility models and applications
- Ensemble learning for portfolio valuation and risk management
- Leveraging machine learning for high-dimensional option pricing within the uncertain volatility model
- Deep Feynman-Kac methods for high-dimensional semilinear parabolic equations: revisit
- Significance of predictors: revisiting stock return predictions using explainable AI
This page was built for publication: Machine learning for pricing American options in high-dimensional Markovian and non-Markovian models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4991044)
