TY - JOUR
T1 - Generalizing the Theta method for automatic forecasting
AU - Spiliotis, Evangelos
AU - Assimakopoulos, Vassilios
AU - Makridakis, Spyros
PY - 2020
Y1 - 2020
N2 - The Theta method became popular due to its superior performance in the M3 forecasting competition. Since then, although it has been shown that Theta provides accurate forecasts for various types of data, being a solid benchmark to beat, limited research has been conducted to exploit its full potential and generalize its reach. This paper examines three extensions on Theta's framework to boost its performance. This includes (i) considering both linear and non-linear trends, (ii) allowing to adjust the slope of such trends, and (iii) introducing a multiplicative expression of the underlying forecasting model along with the existing, additive one. The proposed modifications transform Theta into a generalized forecasting algorithm, suitable for automatic time series predictions. The proposed algorithm is evaluated using the series of the M, M3, and M4 competitions. Such an evaluation shows that the proposed approach produces more accurate forecasts than the original, classic Theta, both in terms of point forecasts and prediction intervals, and is also more accurate than other well-known methods for yearly series.
AB - The Theta method became popular due to its superior performance in the M3 forecasting competition. Since then, although it has been shown that Theta provides accurate forecasts for various types of data, being a solid benchmark to beat, limited research has been conducted to exploit its full potential and generalize its reach. This paper examines three extensions on Theta's framework to boost its performance. This includes (i) considering both linear and non-linear trends, (ii) allowing to adjust the slope of such trends, and (iii) introducing a multiplicative expression of the underlying forecasting model along with the existing, additive one. The proposed modifications transform Theta into a generalized forecasting algorithm, suitable for automatic time series predictions. The proposed algorithm is evaluated using the series of the M, M3, and M4 competitions. Such an evaluation shows that the proposed approach produces more accurate forecasts than the original, classic Theta, both in terms of point forecasts and prediction intervals, and is also more accurate than other well-known methods for yearly series.
KW - Automatic model selection
KW - Forecasting
KW - M competitions
KW - Theta method
KW - Time series
UR - http://www.scopus.com/inward/record.url?scp=85078801969&partnerID=8YFLogxK
U2 - 10.1016/j.ejor.2020.01.007
DO - 10.1016/j.ejor.2020.01.007
M3 - Article
AN - SCOPUS:85078801969
SN - 0377-2217
JO - European Journal of Operational Research
JF - European Journal of Operational Research
ER -