Prediction of Option Prices by BP Neural Network Based on Principal Component Analysis

Under the development of artificial intelligence, this paper adopts the neural network algorithm based on principal component analysis to perform data fitting and prediction on the option prices of Huaxia SSE 50ETF. It also compares the fitting and prediction accuracy of the traditional Black-Scholes option pricing, time series option pricing model and BP neural network algorithm based on principal component analysis for option prices. For the time series model, by analyzing the ACF and PACF figures, the research builds an ARIMA(2,2,0) model. For Black-Scholes model, the study utilizes the relevant stock price information to build the model. The results show that the prediction of BP neural network algorithm based on principal component analysis is effective, and it has the highest fitting and prediction accuracy. The fitting accuracy of the traditional time series option pricing method is approximately the same as that of the Black-Scholes model, but the prediction accuracy of Black-Scholes is relatively higher.