Visualising forecasting algorithm performance using time series instance spaces

By Yanfei Kang, Rob J Hyndman, K. Smith‐Miles. 2017

174 citations recorded by the source corpus.

It is common practice to evaluate the strength of forecasting methods using collections of well-studied time series datasets, such as the M3 data. The question is, though, how diverse and challenging are these time series, and do they enable us to study the unique strengths and weaknesses of different forecasting methods? This paper proposes a visualisation method for collections of time series that enables a time series to be represented as a point in a two-dimensional instance space. The effectiveness of different forecasting methods across this space is easy to visualise, and the diversity of the time series in an existing collection can be assessed. Noting that the diversity of the M3 dataset has been questioned, this paper also proposes a method for generating new time series with controllable characteristics in order to fill in and spread out the instance space, making our generalisations of forecasting method performances as robust as possible.

Subfields: Computer Vision and Pattern Recognition, Management Science and Operations Research, Signal Processing

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Management Science and Operations Research

In Signal Processing

Citations in the corpus

FFORMA: Feature-based forecast model averaging (2020, methodology): “There have been several previous attempts to use time series features combined with metalearning for forecasting, both for model selection and combination (see for example Prudêncio & Ludermir 2004; Lemke & Gabrys 2010; Kück, Crone & Freitag 2016; and Kang, Hyndman & Smith-Miles 2017).”
Forecast combinations: An over 50-year review (2022, background): “Moreover, given the considerable literature on feature identification and feature engineering (e.g., Wang et al., 2009; Kang et al., 2017; Lemke and Gabrys, 2010; Montero-Manso et al., 2020; Li et al., 2020), the feature-based forecast combination methods naturally raise some issues yet to receive m”
Tales from tails: On the empirical distributions of forecasting errors and their implication to risk (2019, background): “Furthermore, depending on the type of the time series examined, e.g. based on their frequency and domain, diﬀerent levels of accuracy might be feasible (Kang et al., 2017).”