Calibration of European option pricing model using a hybrid structure based on the optimized artificial neural network and Black-Scholes model
نویسندگان
1 Department of Applied Mathematics, Faculty of Mathematical Science, University of Guilan
2 Department of Applied Mathematics, Faculty of Mathematical Science, University of Guilan.
doi
10.22054/jmmf.2024.78910.1128چکیده
This study suggests a novel approach for calibrating European option pricing model by a hybrid model based on the optimized artificial neural network and Black-Scholes model. In this model, the inputs of the artificial neural network are the Black-Scholes equations with different maturity dates and strike prices. The presented calibration process involves training the neural network on historical option prices and adjusting its parameters using the Levenberg-Marquardt optimization algorithm. The resulting hybrid model shows superior accuracy and efficiency in option pricing on both in sample and out of sample dataset.
