Paper: arXiv 2310.16703

Authors: Kentaro Hoshisashi, Carolyn E. Phelan, Paolo Barucca

Abstract

Volatility smile and skewness are two key properties of option prices that are represented by the implied volatility (IV) surface. However, IV surface calibration through nonlinear interpolation is a complex problem due to several factors, including limited input data, low liquidity, and noise. Additionally, the calibrated surface must obey the fundamental financial principle of the absence of arbitrage, which can be modeled by various differential inequalities over the partial derivatives of the option price with respect to the expiration time and the strike price. To address these challenges, we have introduced a Derivative-Constrained Neural Network (DCNN), which is an enhancement of a multilayer perceptron (MLP) that incorporates derivatives in the objective function. DCNN allows us to generate a smooth surface and incorporate the no-arbitrage condition thanks to the derivative terms in the loss function. In numerical experiments, we train the model using prices generated with the SABR model to produce smile and skewness parameters. We carry out different settings to examine the stability of the calibrated model under different conditions. The results show that DCNNs improve the interpolation of the implied volatility surface with smile and skewness by integrating the computation of the derivatives, which are necessary and sufficient no-arbitrage conditions. The developed algorithm also offers practitioners an effective tool for understanding expected market dynamics and managing risk associated with volatility smile and skewness.

Complexity vs Empirical Score

  • Math Complexity: 8.5/10
  • Empirical Rigor: 5.5/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper is heavily mathematical, involving stochastic calculus, PDEs, and neural network derivative constraints, while also demonstrating practical implementation and empirical stability tests using synthetic SABR data.

Research Flowchart

  flowchart TD
  A["Research Goal: Calibrate IV surface with smile/skewness under no-arbitrage constraints"] --> B["Input: Option Prices from SABR Model"]
  B --> C["Methodology: Derivative-Constrained Neural Network DCNN"]
  C --> D["Computation: MLP training with no-arbitrage differential inequalities"]
  D --> E["Output: Smooth Arbitrage-Free IV Surface"]
  E --> F["Outcome: Improved interpolation stability & risk management"]

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 Derivative-Constrained Neural Network (DCNN) that extends a multilayer perceptron with derivative terms in the loss to calibrate the implied volatility surface while enforcing no‑arbitrage constraints.

Source sentence
we have introduced a Derivative-Constrained Neural Network (DCNN), which is an enhancement of a multilayer perceptron (MLP) that incorporates derivatives in the objective function.

Assumes 5

  • Option price data are sparse, requiring interpolation or additional information. data
    Source sentence
    The challenge of this inverse problem is the scarcity of options price data.
  • The SABR model parameters (α=0.2, β=1.0, ν=0.6, ρ=−0.4) generate synthetic option prices for training. model
    Source sentence
    ... α = 0.2, β = 1.0, q = 0, and r = 0.04 as the parameters of the SABR model.
  • No‑arbitrage conditions are represented by sign constraints on first and second derivatives of the call price. model
    Source sentence
    The necessary and sufficient conditions for no‑arbitrage are represented as non‑strict inequalities for several first and second derivatives, −e^{−rτ} ≤∂C/∂K ≤0
  • Random seeds are fixed across experiments for statistical consistency. statistical
    Source sentence
    We consistently used the same random seeds across different conditions for the statistical analysis and changed these seed values ten times.
Show 1 more
  • Automatic differentiation provides exact derivative values for the penalty terms. other
    Source sentence
    DCNN allows us to generate a smooth surface and incorporate the no‑arbitrage condition thanks to the derivative terms in the loss function.

Data

  • S&P 500 call options intraday dataset · Yahoo finance library options public
    10th to 14th July 2023 · S&P 500 call options
    Source sentence
    The empirical experiments were conducted using intraday prices for S&P 500 call options from 10th to 14th July 2023; we obtained about two thousand points on a daily basis via the Yahoo finance library as Table 1.
  • Synthetic SABR‑generated option prices synthetic unknown
    Source sentence
    In numerical experiments, we train the model using prices generated with the SABR model to produce smile and skewness parameters.

Recognised sources: Yahoo Finance

Costs

Not applicable The paper reports no trading or execution result.

Finds 4

  • DCNN improves interpolation of the premium surface for volatility smile and skewness compared with cubic spline and standard MLP. pricing-calibration
    Source sentence
    DCNN significantly improved the interpolation of the premium surface for volatility smile and skewness due to deep learning with no‑arbitrage constraints.
  • DCNN produces fewer violations of the no‑arbitrage derivative constraints, as shown by reduced red‑coloured areas in derivative plots. theoretical
    Source sentence
    In Figure 9, we see that the plots for DCNN have fewer areas in red, denoting the regions where the no‑arbitrage conditions on the derivatives are broken.
  • During training, the penalty associated with derivative terms decreases, indicating a balance between price accuracy and no‑arbitrage compliance. performance
    Source sentence
    The findings demonstrate that as the learning process proceeds, there’s a decrease in the penalty associated with the derivative term, reflecting a balance between accuracy and penalty from derivative terms.
  • DCNN effectively enforces the sign constraints on first and second derivatives of the call price, satisfying the necessary no‑arbitrage conditions. theoretical
    Source sentence
    DCNN effectively ensures that the results do not infringe on the conditions for derivative values, each of which aligns with an inequality constraint in Eq. (3).

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 23 related papers). Coverage is partial, so this is neither replication nor refutation.

Cited by 4 papers in the archive (3 by independent authors)

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.