Combining exponential smoothing forecasts using Akaike weights

By Stephan Kolassa. 2011

109 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

'Horses for Courses' in demand forecasting (2014, methodology): “Many recent studies have verified that the combination of methods leads to more accurate forecasts, whilst, at the same time proposing more sophisticated weightings such as the trimmed and Winsorized means (Jose and Winkler, 2008), and the use of information criteria (Taylor, 2008; Kolassa, 2011).”
Forecasting with temporal hierarchies (2017, background): “Finally Section 7 demonstrates their use and benefits in a case study of Accident & Emergency departments, followed by concluding remarks.”
Improving forecasting by estimating time series structural components across multiple frequencies (2014, methodology): “Many recent studies have examined sophisticated weight selection processes for combining forecasts (He and Xu, 2005; Taylor, 2008; Kolassa, 2011); however, simple approaches are considered to be robust and perform reasonably well relative to more complex methods (Clemen, 1989; Hibon and Evgeniou,…”
Forecasting in social settings: The state of the art (2020, background): “Current approaches to forecast combinations include, among others, combinations based on information criteria (Kolassa, 2011), the use of multiple temporal aggregation levels (Andrawis et al., 2011; Kourentzes et al., 2014; Athanasopoulos et al., 2017), bootstrapping for time series forecasting…”
Forecasting: theory and practice (2020, methodology): “Kolassa (2011) apply so called Akaike weights based on Akaike Information Criterion (Sakamoto et al., 1986), while bootstrapping has been used to generate and combine forecast from exponential smoothing (Cordeiro and Neves, 2009; Barrow et al., 2020; Bergmeir et al., 2016), artificial neural…”
Statistical models underlying functions of 'smooth' package for R (2017, methodology): “Some functions allow to combine forecasts of models using information criteria weights, discussed by Kolassa (2011) and in Burnham and Anderson (2004) (currently only es() has it, but this is to be implemented for ssarima() and some other functions as well).”
Exploring the sources of uncertainty: Why does bagging for time series forecasting work? (2018, methodology): “The gains are even more evident if one focuses on the M3-competition data set, which conﬁrms the ﬁndings of Kolassa (2011).”
Forecast combinations: An over 50-year review (2022, methodology): “For instance, Kolassa (2011) used weights derived from AIC, AICc and BIC to combine exponential smoothing forecasts, and obtained superior accuracy over selecting a model using the same information criteria.”