基于BP神经网络的改进粒子群优化股票预测

Stock Forecasting Based on BP Neural Network Optimized by Improved Particle Swarm Optimization

可以以较为精准的预测结果为依据来对股票市场进行及时指引与调控,这样更能保障我国国民经济的可持续顺利发展。本文的目的是研究改进的基于粒子群优化算法的改进版BP神经网络股票预测,这种神经网络预测方法是以粒子群优化算法为基础并将其应用于股市预测,取得了较好的效果。详细给出了基于粒子群算法的神经网络模型的建立方法,同时本文还比较了PSO-BP网络引入定性指标前后的性能,通过对股票指数和股票价格的预先测评,实验结果表明了,PSO-BP神经网络具有相对优势性。因为其趋势预测准确率提高了7%,预测偏差MAE降低了5。

With more accurate prediction results, we can guide and regulate the stock market in time, so as to provide an important guarantee for the sustainable and healthy development of China’s national economy. The purpose of this paper is to study the improved BP neural network stock prediction based on particle swarm optimization algorithm,and put forward the neural network prediction method based on particle swarm optimization algorithm, and applied it to the stock market prediction, and achieved good results. At the same time, this paper compares the performance of PSO-BP network before and after the introduction of qualitative indicators. Through the prediction of stock index and stock price, the experimental results show that the prediction error MAE of PSO-BP network is reduced by 5, and the accuracy of trend prediction is increased by 7%, which proves the relative superiority of PSO-BP neural network.