基于PSO-BP神经网络的上证指数股票预测模型应用研究
首发时间:2018-05-16
摘要:随着国民经济的飞速发展以及市场经济的不断完善,股票投资成为了现代人投资理财中的一个重要部分。股价的波动直接影响着股票市场的稳定以及金融与经济的健康发展。成功的股价和趋势预测有助于投资者获利,也有利于政府部门提供及时合理的市场指导与监管。因此,如何准确预测股票市场是一个重要而有价值的课题。现今,大量人工智能和机器学习技术被应用于股票市场的预测中,而反向传播神经网络(BPNN)更是智能预测中使用最为广泛的技术之一。但BP神经网络具有局部搜索能力强,全局搜索能力弱的缺点。因此,本文在其基础上加入了具有强全局搜索能力的粒子群优化算法(PSO),提出了一种将PSO算法用于训练BP神经网络初始权重的混合算法,并称之为PSO-BP神经网络算法。本文通过PSO-BP神经网络对上证指数收盘价进行实证分析,探讨了样本指标、数据的选取;网络的拓扑结构的构成;隐含层节点个数及激活函数的选取等问题。同时,我们也给出同样是智能混合算法的GA-BP神经网络算法并加以比较。实验结果表明,在模拟与预测的效果上,混合PSO-BP神经网络算法均优于GA-BP神经网络算法与BP神经网络算法;且能够较为准确的预测出近一段时间上证指数的收盘价格与未来涨跌情况,模型有着良好的应用前景。
For information in English, please click here
Research on Application of Shanghai Stock Index Prediction Model Based on PSO-BP Neural Network
Abstract:With the rapid development of the national economy and the continuous improvement of the market economy, stock investment has become an important part of modern people\'s investment and financial management. The fluctuation of the stock price directly affects the stability of the stock market and the healthy development of finance and economy. Successful forecasting of stock prices and trends helps investors to make profits, and it also helps government departments provide timely and reasonable market guidance and supervision. Therefore, how to accurately predict the stock market is an important and valuable issue. Nowadays, a large number of artificial intelligence and machine learning technologies have been used in the prediction of the stock market, and back propagation neural network (BPNN) is one of the most widely used technologies in intelligent prediction. However, BP neural network has the disadvantages of strong local search ability and weak global search ability. Therefore, this paper adds a particle swarm optimization (PSO) algorithm with strong global search capability and proposes a hybrid algorithm that uses PSO algorithm to train the initial weights of BP neural network. It is called PSO-BP neural. Network algorithm.This paper uses PSO-BP neural network to empirically analyze the closing price of the Shanghai Stock Exchange Index, discusses the selection of sample indexes and data, the topology structure of the network, the number of hidden layer nodes, and the selection of activation functions. At the same time, we also give GA-BP neural network algorithms that are also intelligent hybrid algorithms and compare them.The experimental results show that the mixed PSO-BP neural network algorithm is superior to the GA-BP neural network algorithm and BP neural network algorithm in the simulation and prediction effect, and can accurately predict the closing price of the Shanghai index in the near future. In the future, the model has a good application prospect.
Keywords: BP neural network PSO algorithm stock prediction
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
基于PSO-BP神经网络的上证指数股票预测模型应用研究
评论
全部评论0/1000