基于PCA和IFOA-BP神经网络的股价预测模型

针对基于BP神经网络的股票价格预测模型在价格预测时存在较大误差的问题,在BP神经网络方法的基础上引入了主成分分析方法(PCA)和改进的果蝇算法(IFOA),提出一种基于PCA-IFOA-BP神经网络的股票价格预测模型。通过PCA对股票历史数据进行降维,减少冗余信息;采用改进的果蝇算法优化BP神经网络的初始权值和阈值;建立基于PCA和IFOA-BP神经网络的股票价格预测模型。对上证指数股票价格数据进行仿真验证,仿真结果表明:在股票价格预测中,该模型比BP神经网络、PCA-BP和PCA-FOA-BP的预测精度更高,是一种有效可行的预测方法。

A PREDICTION MODEL OF STOCK PRICE BASED ON PCA AND IFOA-BP NEURAL NETWORK

Aiming at the problem of large price error in stock price forecasting model based on BP neural network,this paper introduces principal component analysis(PCA)and improved fruit fly algorithm(IFOA)based on BP neural network method,and proposes a stock price forecasting model based on PCA-IFOA-BP neural network.We used PCA to reduce the dimension of stock historical data and reduced redundant information.Then,a novel improved fruit fly optimization algorithm was utilized to optimize the initial weights and threshold of BP neural network.We established a stock price forecasting model based on PCA and IFOA-BP neural network algorithm.Stock price data of Shanghai composite index was verified by simulation.Simulation results show that our model has higher prediction accuracy than BP neural network,PCA-BP and PCA-FOA-BP in the prediction of stock price,which is an effective and feasible prediction method.