Forecasting of Sporadic Demand Patterns with Seasonality and Trend Components: An Empirical Comparison between Holt-Winters and (S)ARIMA Methods
Table 4
Comparison between (S)ARIMA and HW based on MSE/.
Series
Group
MSE/ 5 time periods ahead
MSE/ 12 time periods ahead
(S)ARIMA
HW
(S)ARIMA
HW
s1
1
6.8%
6.8%
27.0%
22.4%
s2
59.3%
79.6%
73.0%
74.2%
s3
33.0%
41.8%
469.9%
111.5%
s4
35.1%
28.2%
43.8%
48.9%
s5
5.1%
20.2%
12.9%
34.5%
s6
2.6%
5.1%
22.0%
7.9%
s7
434.4%
3.9%
10361.6%
10675.5%
s8
2
268.9%
424.1%
801.5%
953.2%
s9
8.3%
666.7%
217.9%
678.6%
s10
9.9%
435.9%
80.8%
502.4%
s11
60.3%
463.0%
172.9%
1424.8%
s12
529.8%
286.0%
439.7%
1369.8%
We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.
