摘要
针对股票"青岛海尔"的日成交量,选取2016年下半年数据,利用B-J法建立ARMA模型,借助Eviews 8软件的求解,得到与实际数据高度吻合的ARMA(3,2)模型,并对未来4天日成交量进行预测,然后与2017年初的实际数据对比,发现预测结果比较好.结论表明:模型的精确度比较高,适合股票短线也即日成交量的分析与预测.
Based on the trading volume on the stock " Qingdao Haier", selected data of the first half in 2016, ARMA model is established by using the B -J method. The solution of Eviews 8 software was highly consistent with the actual data of ARMA (3,2) model. And carried on the forecast to the future 4 day turnover, the actual data was compared with that at the beginning of 2017. The results show the prediction resuhs are better, the accuracy of the model is relatively high, and it is suitable for the analysis and prediction of the short- term and current stock volume.
出处
《哈尔滨师范大学自然科学学报》
CAS
2016年第6期6-10,共5页
Natural Science Journal of Harbin Normal University
基金
国家自然科学项目(11601001)