Comparison of Artificial Neural Network Architectures for Pricing European Call Options on S&P 500 and NASDAQ 100 Indices

Various artificial neural network architectures, including multilayer perceptron (MLP), Kolmogorov-Arnold network (KAN), LSTM-GRU hybrid recursive neural network (RNN) models, and a time-delay neural network (TDNN), outperform the traditional Black-Scholes model in pricing European call options on the S&P 500 and NASDAQ 100 indices.