摘要:为提高BP神经网络预测模型对混沌时间序列的预测准确性,提出一种基于遗传算法优化BP神经网络的改进混沌时间序列预测方法。本文采用时间序列输入输出参数数量构造BP神经网络拓扑结构,利用遗传算法优化BP神经网络的权值和阈值,然后训练BP神经网络预测模型求得最优解,将该预测方法应用到上证综合指数的时间序列进行有效性验证,结果表明了该方法对上证综合指数具有更好的非线性拟合能力和更高的预测准确性。 关键词:股指预测;混沌理论;BP神经网络;遗传算法
中图分类号:F830.593;TP183 文献标识码:A
半距等高线
The Prediction of Stock Index Based on Genetic Algorithm Optimized Chaotic Neural Network
ewt MA Ming 1,LI Song 2
(1. School of Economics, Peking University, Beijing 100871, China;
教学论坛
ttl 2. School of Management, Hebei University, Baoding 071002, China)
Abstract:In order to improve forecasting model accuracy of BP neural network for chaotic time series, an improved prediction method for chaotic time series of optimized BP neural network based on genetic algorithm (GA) was presented. In this method, the BP neural network topology was constructed by the number of input and output of time series. The GA was used to optimize the weights and thresholds of BP neural network, and then BP neural network was trained to search for the optimal solution. The availability of the proposed prediction method was proved by predicting the time series of Shanghai stock index. The computer simulations have shown that the nonlinear fitting and accuracy of the modified prediction methods were better than BP prediction methods.
Key words:stock index prediction; chaotic theory; BP neural network; genetic algorithm
南艺学分制
数据预测在金融投资领域占有重要地位,而股票指数预测具有变换幅度大,变化因素多,变化
郭超人不稳定等特性,是金融数据中最复杂的数据类型之一,其研究一直是金融理论的研究热点。股票指数具有明显的混沌特征,许多学者对其混沌特性进行了深入研究,建立了多种基于混沌理论的股票指数(价格)预测模型,如BP神经网络模型[1-2]、RBF神经网络模型[3]、小波神经网络[4]等。其中,BP神经网络模型是比较成功的预测模型。但该模型有两个明显的缺点:一是容易于陷入局部极小值;二是收敛速度慢。为克服上述缺点,本文从非线性混沌时间序列角度出发,采用遗传算法(Genetic Algorithm,GA)优化的BP神经网络预测模型,用于沪深股票指数预测。
豫公网安备41160202000603
站长QQ:729038198
关于我们
投诉建议