Paper: arXiv 2407.15536
Authors: Giovanni Amici, Marco Morandotti, Chen Zhang
Abstract
We propose a gradient-based deep learning framework to calibrate the Heston option pricing model (Heston, 1993). Our neural network, henceforth deep differential network (DDN), learns both the Heston pricing formula for plain-vanilla options and the partial derivatives with respect to the model parameters. The price sensitivities estimated by the DDN are not subject to the numerical issues that can be encountered in computing the gradient of the Heston pricing function. Thus, our network is an excellent pricing engine for fast gradient-based calibrations. Extensive tests on selected equity markets show that the DDN significantly outperforms non-differential feedforward neural networks in terms of calibration accuracy. In addition, it dramatically reduces the computational time with respect to global optimizers that do not use gradient information.
Complexity vs Empirical Score
- Math Complexity: 8.0/10
- Empirical Rigor: 7.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced mathematics including stochastic calculus, Fourier inversion for Heston pricing, and partial derivative analysis, while providing extensive empirical tests on equity markets with performance metrics and computational time reductions.
Research Flowchart
flowchart TD A["Research Goal<br>Accurate & Fast Heston Calibration"] --> B["Data: Market Option Data"] B --> C["Method: Deep Differential Network (DDN)"] C --> D["Compute: Price & Sensitivities"] D --> E["Optimization: Gradient-Based"] E --> F["Outcome: Calibrated Parameters"] F --> G["Key Findings<br>Better Accuracy & Faster Speed"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes a gradient‑based deep learning framework called a deep differential network (DDN) to calibrate the Heston option pricing model.
Source sentence
We propose a gradient-based deep learning framework to calibrate the Heston option pricing model (Heston, 1993).
Assumes 5
- The risk‑free interest rate r is constant. model
Source sentence
r is the continuously compounded risk‑free interest rate (assumed to be constant)
- The Heston model parameters (κ, λ, σ, ρ, v0) are constant over the calibration horizon and not observable in the market. model
Source sentence
is the vector of model parameters, not observable in the market.
- Partial derivatives of the pricing function are obtained by numerical differentiation of the QuantLib pricer because analytical gradients are unavailable. data
Source sentence
we recover the partial derivatives by numerical differentiation of the QuantLib pricer, given that the semi-analytical partial derivatives are not available in QuantLib.
- Training and test data are generated synthetically by pricing vanilla call options with QuantLib using the Lewis‑framework quadrature. data
Source sentence
we generate the dataset used for the neural network training by pricing the call options through the QuantLib engine, which efficiently approximates the integrals of the pricing function by means of exponentially‑fitted Gauss‑Laguerre quadrature in the Lewis framework
Show 1 more
- The network architecture uses Xavier Glorot initialization and a dropout rate of 0.2 to mitigate over‑fitting and gradient issues. other
Source sentence
we regularize the network by dropping out nodes from each layer, setting a dropout rate of 0.2
Data
- Synthetic call‑option dataset generated with QuantLib options unknown
Source sentence
we generate the dataset used for the neural network training by pricing the call options through the QuantLib engine
Yahoo Finance
Costs
Not applicable
Finds 4
- The DDN significantly outperforms non‑differential feedforward neural networks in calibration accuracy on equity markets. pricing-calibration
Source sentence
Extensive tests on selected equity markets show that the DDN significantly outperforms non-differential feedforward neural networks in terms of calibration accuracy.
- The DDN reduces computational time dramatically compared with global optimizers that do not use gradient information. performance
Source sentence
In addition, it dramatically reduces the computational time with respect to global optimizers that do not use gradient information.
- Calibration with the DDN achieves roughly the same accuracy as the Nelder‑Mead method but requires only a few seconds instead of minutes. pricing-calibration
Source sentence
the DDN achieves roughly the same accuracy of the Nelder‑Mead calibration method
- Training times of the DDN are comparable to a typical feedforward network, showing methodological parsimony. performance
Source sentence
the DDN training times roughly correspond to the training times of a typical feedforward neural network in which the differentiation layer is not employed
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 29 related papers). Coverage is partial, so this is neither replication nor refutation.
1 paper in the archive
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.