Exponential smoothing: The state of the art

By Everette S. Gardner Jr.. 1985

Subfields: Statistics and Probability, Time-Series & Forecasting

How researchers see this paper

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

In Statistics and Probability

In Time-Series & Forecasting

Citations in the corpus

Forecasting at Scale (2018, neutral): “Modeling seasonality as an additive component is the same approach taken by exponential smoothing (Gardner 1985).”
Forecasting with a hybrid method utilizing data smoothing, a variation of the Theta method and shrinkage of seasonal factors (2018, methodology): “However, given a completed smoothed time series (straight line), the coefficient of SES will be always forced to one.”
Modelling and Forecasting Australian Domestic Tourism (2006, methodology): “The modelling strategy we follow in this paper is a restricted version of the Hyndman et al. (2002) methodology for innovations state space models, which is based on the taxonomy proposed by Pegels (1969), extended by Gardner (1985) and advocated by Makridakis et al. (1998).”
Smooth transition exponential smoothing (2004, methodology): “The literature generally recommends that the smoothing parameters should be estimated from the data, usually by minimising the sum of ex post 1-step-ahead forecast errors (Gardner, 1985).”
Forecasting: theory and practice (2020, background): “The development of exponential smoothing dates back to 1944, where Robert G. Brown through a mechanical computing device estimated key variables for fire-control on the location of submarines (Gardner, 1985).”
On the identification of sales forecasting models in the presence of promotions (2015, methodology): “Since the 1950s the use of Exponential Smoothing for forecasting has been the most popular forecasting method used in business and industry (Gardner, 2006; Hyndman et al, 2008).”
Improving forecasting by estimating time series structural components across multiple frequencies (2014, methodology): “ETS is a family of methods, designed for forecasting time series with different characteristics, covering a wide range of additive and multiplicative combinations of level, trend, seasonality and noise (Gardner, 1985; Taylor, 2003; Gardner, 2006).”
Robust forecasting with exponential and holt-winters smoothing (2009, methodology): “More details can be found in the review article Gardner (2006).”