The Optimised Theta Method

11 Mar 2015  ·  José Augusto Fioruci, Tiago Ribeiro Pellegrini, Francisco Louzada, Fotios Petropoulos ·

Accurate and robust forecasting methods for univariate time series are very important when the objective is to produce estimates for a large number of time series. In this context, the Theta method called researchers attention due its performance in the largest up-to-date forecasting competition, the M3-Competition. Theta method proposes the decomposition of the deseasonalised data into two "theta lines". The first theta line removes completely the curvatures of the data, thus being a good estimator of the long-term trend component. The second theta line doubles the curvatures of the series, as to better approximate the short-term behaviour. In this paper, we propose a generalisation of the Theta method by optimising the selection of the second theta line, based on various validation schemes where the out-of-sample accuracy of the candidate variants is measured. The recomposition process of the original time series builds on the asymmetry of the decomposed theta lines. An empirical investigation through the M3-Competition data set shows improvements on the forecasting accuracy of the proposed optimised Theta method.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper