ARIMA-GARCH-M模型在短期股票预测中的应用  

Application of ARIMA-GARCH-M model in short-term stock forecasting

作　　者：熊政 车文刚[1] XIONG Zheng;CHE Wen-gang(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《陕西理工大学学报（自然科学版）》2022年第4期69-74,共6页Journal of Shaanxi University of Technology:Natural Science Edition

摘　　要：金融时间序列模型既是股票预测中最常用的方法,也是预测股市变化最好的工具之一。根据已有研究,将波动率代入模型公式中,根据各项准则构建ARIMA-GARCH-M模型对股票的收盘价进行预测,利用递归思想对拟合曲线进行校正,进一步提高预测的准确率,并进行MAPE(平均绝对误差)、RMSE(均方根误差)、EC(等系数)检验。最后将ARIMA模型、ARIMA-GARCH模型和ARIMA-GARCH-M模型的检验结果比较。结果表明,通过递归校正的ARIMA-GARCH-M模型在股票短期预测中有着良好的效果,具有一定的可行性。Financial time series model is the most commonly used method in stock forecasting,and it is also one of the best tools to predict the changes of stock market.According to the latest research available,the volatility is substituted into the model formula,the ARIMA-GARCH-M model is constructed according to various criteria to predict the closing price of“Ping An Bank”,and the recursive idea is used to correct the fitting curve to further improve the accuracy of prediction.It is tested by MAPE(mean absolute error),RMSE(root mean square error)and EC(equal coefficient).Finally,the test results of ARIMA model,ARIMA-GARCH model and ARIMA-GARCH-M model are compared.The results show that the ARIMA-GARCH-M model with recursive correction is effective and feasible in the short-term prediction of Ping An Bank’s stock.

关 键 词：股票预测 ARIMA模型 ARIMA-GARCH模型 ARIMA-GARCH-M模型 时间序列 

分 类 号：TP133.5[自动化与计算机技术—控制理论与控制工程]