Optimizing the prediction of financial market price fluctuations and constructing more effective financial market price prediction models has always been a research topic of great interest to both the academic and practical communities in the field of financial markets. To this end, this paper combines BP neural network technology with principal component analysis (PCA) to construct a stock price prediction model based on PCA-BP neural networks. This paper selects the CSI 300 Index as the research object and conducts empirical analysis using the stock price prediction model constructed in this paper. The results show that the model has the highest prediction accuracy. In the directional accuracy analysis on December 5, the accuracy rate reached 92.63%, which can provide decisionmaking basis for investors and regulators to a certain extent.
