Robert Fildes asked me to prepare a review of exponential smoothing for OR60. I thought that it would be boring just to look in the past, so I decided to do past + present + future, adding a model that Nikos and I have started working on some time ago (GUM – Generalised Univariate Model). In the end, the presentation was very dense and I hardly managed to fit in 30 minutes.
Here’s the abstract:
Exponential smoothing has been known in both theoretical and practical forecasting for more than 60 years. It has evolved substantially from a simple exponential smoothing method, aiming at dealing with level data to a state-space framework, covering various time series characteristics. In this presentation we discuss the key milestones in the development of exponential smoothing, show the connections between the exponential smoothing and the other forecasting models and, finally, propose a more general framework that can potentially encompass all the existing forecasting models, called “Generalised Univariate Model”.