问题描述
我正在尝试使用 ARIMA 对 R 中的股票价格进行预测.我正在使用 auto.arima 函数来拟合我的模型.每次我尝试这样做时，我都会得到相同的预测值.我尝试使用不同的股票，但在每种情况下都会发生同样的事情.在这里，我尝试预测苹果价格:
I am trying to do forecasting of stock prices in R using ARIMA. I am using the auto.arima function to fit my model. Every time I'm trying to do that I get the same value for the forecasted values. I tried using different stocks but the same thing happens in every case. Here I tried forecasting apple prices:
arimapple <- ts(appletrain, start = timedata[1])
fitappletrain <- auto.arima(arimapple)
fitappletrain <- auto.arima(arimapple)
fitappletrain
fitappletrain
forecastapple <- forecast(fitappletrain, h=57)
forecastapple <- forecast(fitappletrain, h=57)
预测苹果
我得到的输出如下:
Point Forecast Lo 80 Hi 80 Lo 95 Hi 95
17763 180.94 176.7350 185.1450 174.5090 187.3710
17764 180.94 174.9932 186.8868 171.8451 190.0349
17765 180.94 173.6567 188.2233 169.8011 192.0789
17766 180.94 172.5299 189.3501 168.0779 193.8021
17767 180.94 171.5373 190.3427 166.5598 195.3202
17768 180.94 170.6398 191.2402 165.1872 196.6928
17769 180.94 169.8145 192.0655 163.9251 197.9549
17770 180.94 169.0464 192.8336 162.7503 199.1297
17771 180.94 168.3249 193.5551 161.6469 200.2331
等等，所以我收到的每个预测都是 180.94.我该如何解决这个问题?
and so on, so every forecast I receive is 180.94. How can I solve this?
推荐答案
我认为你的数据不包含任何强烈的季节性和趋势，我认为您的历史数据也较少，因此 auto.arima() 无法准确找到预测.
I think your data does not contain any strong seasonality and trend and i thinkyour historical data is also less, the auto.arima() is not able to find forecast accurate because of that.
因此，它只是取历史数据的平均值并作为预测返回.因此值是相同的(绘制时会得到直线.)
Therefore it is simply taking average of your historical data and returning as forecast.therefore the values are same (you will get straight line when you plot it.)
这篇关于R 中 ARIMA 预测的相同值的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！