摘要
金融市场上的时间序列数据蕴含了历史信息,可以揭示系统的运行规律。研究者们可以采用常见的时间序列分析模型,借助Eviews等工具,对以往的金融数据(如股价)进行研究,探寻其规律,并运用于未来走势的短期预测。选取工商银行(601398)的股票日开盘价(2018月2月14日至2019年2月14日)序列,进行一阶差分使数据平稳,之后运用ARMA模型对未来三天的开盘价(2019年2月15日至2019年2月19日)进行预测。将预测结果与真实值对比后发现预测结果较为准确,误差较小,说明ARMA模型适合于股价短期预测,进一步证实了时间序列模型在金融方面的作用。
The time series data in the financial market contain historical information,which can reveal the operating rules of the system.Researchers can use common time series analysis models and Eviews and other tools to study past financial data(such as stock prices) to explore their laws and apply them to short-term prediction of future trends.Select the daily opening price(2018-02-14 to2019-02-14) sequence of industrial and commercial bank of China(601398),make first-order difference to stabilize the data,and then use ARMA model to predict the opening price(2019-02-15 to 2019-02-19)in the next three days.Comparing the predicted results with the real values,it is found that the predicted results are more accurate and the error is smaller,which shows that ARMA model is suitable for short-term stock price prediction.This further confirms the role of the time series model in finance.
作者
徐晨萌
方华
XU Chen-meng;FANG Hua(Business School,University of Shanghai for Science and Technology,Shanghai 200093,China)
出处
《经济研究导刊》
2019年第31期77-82,共6页
Economic Research Guide
