Emese Lazar

This paper explores the application of neural networks to improve pricing of American options. Focusing on both American and European options on the S&P 100 index from January 2016 to August 2023, we integrate neural networks to model the difference between market‐implied and model‐implied volatilities derived from the Black‐Scholes and Heston models. We also employ a pure neural network which does not use pricing models. Our study compares two neural network training architectures: independent training, where the network is trained anew daily, and sequential training, which uses the previous day's network setup as starting point to retrain the network. The findings reveal that a pure neural network with sequential training significantly reduces the root mean square error (RMSE) of implied volatility predictions compared to traditional pricing models. The inclusion of European option data in the training can enhance the models' forecasting performance, though its effectiveness varies depending on market conditions.

Measuring model risk is required by regulators in financial and insurance markets. We separate model risk into parameter estimation risk (PER) and model specification risk (MSR), and we propose expected shortfall type model risk measures applied to Lévy jump, affine jump-diffusion, and multifactor models. We investigate the impact of PER and MSR on the models’ ability to capture the joint dynamics of stock and option prices. Using Markov chain Monte Carlo techniques, we implement two methodologies to estimate parameters under the risk-neutral probability measure and the real-world probability measure jointly.

We propose a sequential monitoring scheme to detect changes in dynamic semiparametric risk models that capture Value–at–Risk (VaR) and Expected Shortfall (ES) jointly. The monitoring scheme is based on a gradient–based detector and a boundary function, and a change is detected when the detector crosses the boundary function. We derive the asymptotic limit of the stopping time of detection under the null hypothesis of no change. Monte Carlo simulations show that the proposed test has good size control under the null hypothesis and high power under alternative hypotheses of various change point scenarios in finite samples. Empirical applications based on the S&P 500 index and the GBP/EUR exchange rate illustrate that our proposed test is able to detect change points in real–time.