集成模型ARIMAX-GARCH及其在股票预测中的应用  

Integrated Model ARIMAX GARCH and Its Applications in Stock Forecast

作　　者：沈小欣[1] 赵亚玲[1] 朱海江[1] 

机构地区：[1]浙江师范大学数理信息学院,浙江金华321004

出　　处：《绍兴文理学院学报》2014年第9期60-63,共4页Journal of Shaoxing University

摘　　要：在分析ARIMAX模型与GARCH模型的预测特性和优劣的基础上,建立了基于两者集成的ARIMAX-GARCH模型,其基本思想是充分发挥两种模型在回归与序列波动性因素提取方面的优势.对从5大行业中随机抽取的10只只股票的实证分析表明,该集成模型在股票预测中的准确率与稳定性显著优于两个单一模型.Based on the analysis of the performance of multiple stationary time series of ARIMAX and GARCH models, this paper sets up a new model which integrates ARIMAX with GARCH. The new model has the advantage of regression in ARIMAX and the superiority of extracting volatility in GARCH. The result of empirical analysis about ten shares from five industries which are grabbed at random shows that the proposed model has better accuracy and stability in stock forecast than every single model.

关 键 词：时间序列 ARIMAX模型 GARCH模型 ARIMAX—GARCH模型 股票预测 

分 类 号：F224.9[经济管理—国民经济] O213.9[理学—概率论与数理统计]