Construction and Optimization of a Prediction Model for Shenzhen Component Index Price Changes Based on a BP Neural Network

School of Computer and Big Data, Heilongjiang University, Harbin, Heilongjiang Province, 150080, China

^* Corresponding author: Che.Yuexuan@fayettetech.edu

Abstract

In the increasingly complex and dynamic global financial markets, the Shenzhen Component Index (Shenzhen Index), as one of the core indices of China's securities market, has garnered extensive attention from both investors and researchers. Price swings in the Shenzhen Index are due to many different complex reasons making it quite difficult to predict prices accurately. With the growth of AI technology, the Backpropagation Neural Network (BP Neural Network), known for its strong non-linear matching and adaptive qualities, is becoming a more significant tool used in predicting market movements. This research is aimed at improving and building a BP Neural Network model, trying to increase how well it can predict Shenzhen Index price changes. In this paper, efforts are made to optimize the structure and parameters of the BP Neural Network model to offer more precise guidance to investors and fill certain blanks in the existing literature. It is thus represented from the results that the use of the BP neural network is very effective for the leading price fluctuation prediction of the Shenzhen Index. This paper offers a theoretical and practical guide which may be beneficial for subsequent applications within the area of financial time series prediction.