Calibration of European Option Pricing Model in Uncertain Environment Using an Artificial Neural Network

In this paper, we introduce a novel methodology for calibrating European option pricing within the context of uncertain financial markets. Our approach leverages an artificial neural network, where each input neuron corresponds to the option price function derived from the uncertain stock model. We investigate our method against traditional calibration techniques, including those based on uncertain differential equations and the Black–Scholes model. Numerical experiments demonstrate that the proposed neural network-based strategy significantly enhances the accuracy and performance of option price calibration, yielding improved results for both in-sample and out-of-sample datasets.