A neural network-based framework for financial model calibration
From MaRDI portal
Publication:2022121
Abstract: A data-driven approach called CaNN (Calibration Neural Network) is proposed to calibrate financial asset price models using an Artificial Neural Network (ANN). Determining optimal values of the model parameters is formulated as training hidden neurons within a machine learning framework, based on available financial option prices. The framework consists of two parts: a forward pass in which we train the weights of the ANN off-line, valuing options under many different asset model parameter settings; and a backward pass, in which we evaluate the trained ANN-solver on-line, aiming to find the weights of the neurons in the input layer. The rapid on-line learning of implied volatility by ANNs, in combination with the use of an adapted parallel global optimization method, tackles the computation bottleneck and provides a fast and reliable technique for calibrating model parameters while avoiding, as much as possible, getting stuck in local minima. Numerical experiments confirm that this machine-learning framework can be employed to calibrate parameters of high-dimensional stochastic volatility models efficiently and accurately.
Recommendations
- Deep calibration of financial models: turning theory into practice
- Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models
- On a neural network to extract implied information from American options
- Deep neural network framework based on backward stochastic differential equations for pricing and hedging American options in high dimensions
- Neural network calibrated stochastic processes: forecasting financial assets
Cites work
- A closed-form solution for options with stochastic volatility with applications to bond and currency options
- A novel pricing method for European options based on Fourier-cosine series expansions
- A Stochastic Approximation Method
- A theory of the term structure of interest rates
- An inverse problem of determining the implied volatility in option pricing
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
- Asymptotic formulae for implied volatility in the Heston model
- Bayesian calibration of computer models. (With discussion)
- Deep learning
- Differential evolution -- a simple and efficient heuristic for global optimization over continuous spaces
- Error bounds for approximations with deep ReLU networks
- Full and fast calibration of the Heston stochastic volatility model
- scientific article; zbMATH DE number 3388498 (Why is no real title available?)
- Lower bounds for approximation by MLP neural networks
- Machine learning for quantitative finance: fast derivative pricing, hedging and fitting
- The inverse problem of option pricing
Cited in
(33)- Neural network calibrated stochastic processes: forecasting financial assets
- Explainable neural network for pricing and universal static hedging of contingent claims
- Smiles \& smirks: volatility and leverage by jumps
- Precise option pricing by the COS method -- how to choose the truncation range
- Parameter calibration with stochastic gradient descent for interacting particle systems driven by neural networks
- The deep parametric PDE method and applications to option pricing
- Deep calibration of financial models: turning theory into practice
- Analysis on block chain financial transaction under artificial neural network of deep learning
- Calibrating rough volatility models: a convolutional neural network approach
- Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models
- Artificial neural network for option pricing with and without asymptotic correction
- An unsupervised deep learning approach to solving partial integro-differential equations
- Unbiased deep solvers for linear parametric PDEs
- On a neural network to extract implied information from American options
- Meshless methods for American option pricing through physics-informed neural networks
- Applications of artificial neural networks to simulating Lévy processes
- Stochastic processes adapted by neural networks with application to climate, energy, and finance
- Approximation of single-barrier options partial differential equations using feed-forward neural network
- Approximation rates for deep calibration of (rough) stochastic volatility models
- A gradient-based calibration method for the Heston model
- Neural network empowered liquidity pricing in a two-price economy under conic finance settings
- Deep calibration with random grids
- The calibration of volatility for european option under fractional stochastic interest rate model
- From characteristic functions to multivariate distribution functions and European option prices by the (damped) COS method
- On deep learning for computing the dynamic initial margin and margin value adjustment
- Accelerating SDE simulation through learning of stochastic dynamics
- Deep learning in finance: a review of deep hedging and deep calibration techniques
- Deep joint learning valuation of Bermudan swaptions
- Fourier neural network approximation of transition densities in finance
- Joint deep calibration of the 4-factor PDV model
- Deep learning meets extreme values: the neural Hill estimator
- Efficient simulation and calibration of the rough Bergomi model via Wasserstein distance
- Deep learning for derivatives pricing: a comparative study of asymptotic and quasi-process corrections
This page was built for publication: A neural network-based framework for financial model calibration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2022121)
