BP神经网络在基金价格预测中的应用研究  

Application Research of Fund Net Value Prediction Based on BP Neural Network

作　　者：肖国荣[1] 

机构地区：[1]广东金融学院计算机科学与技术系,广东广州510521

出　　处：《计算机仿真》2011年第3期373-376,共4页Computer Simulation

摘　　要：研究基金价格变化的准确预测问题。针对基金价格变化规律相当复杂,影响因素间非线性程度相当的高,传统预测方法不能很好反映非线性规律,导致基金价格预测精度不高。为了基金价格预测精度,提出一种基于BP神经网络的基金价格预测模型。通过BP神经网络优异的非线性逼近能力和自学习能力对基金价格数据进行训练和预测,同时通过自适应学习速率动态地调速BP神经网络学习速率,对基金价格进行预测。通过对金泰基金的仿真研究,表明了改进的BP神经网络比其它基金价格预测具有更高的精确度,能准确地捕捉基金价格的变化趋势,为基金价格预测提供了参考。Research on the problem of predicting fund net value.Because fund net value has many affecting factors,there are nonlinear relations between fund net value and its influence factors.This paper use BP neural network to predict fund net value.The traditional BP neural network has the defects of slow training speed,easy in local minimum,thus leading to the low prediction accuracy,in order to improve the fund net value prediction accuracy with BP neural network,the paper puts forward an improved BP neural network as the fund net value prediction model.The model,uses adaptive learning rate,so that the performance of the BP neural network is improved.The simulation result based on Jintai fund indicates that the learning speed of improved BP neural networks is faster than traditional BP neural network and has higher prediction precision.It provides a practical method for fund net value prediction.

关 键 词：神经网络 基金价格 基金预测 

分 类 号：TV139.1[水利工程—水力学及河流动力学]