A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition

Souhaib Ben Taieb, Gianluca Bontempi, Amir F. Atiya, Antti Sorjamaa

Research output: Contribution to journalReview ArticleResearchpeer-review

205 Citations (Scopus)


Multi-step ahead forecasting is still an open challenge in time series forecasting. Several approaches that deal with this complex problem have been proposed in the literature but an extensive comparison on a large number of tasks is still missing. This paper aims to fill this gap by reviewing existing strategies for multi-step ahead forecasting and comparing them in theoretical and practical terms. To attain such an objective, we performed a large scale comparison of these different strategies using a large experimental benchmark (namely the 111 series from the NN5 forecasting competition). In addition, we considered the effects of deseasonalization, input variable selection, and forecast combination on these strategies and on multi-step ahead forecasting at large. The following three findings appear to be consistently supported by the experimental results: Multiple-Output strategies are the best performing approaches, deseasonalization leads to uniformly improved forecast accuracy, and input selection is more effective when performed in conjunction with deseasonalization.
Original languageEnglish
Pages (from-to)7067-7083
Number of pages17
JournalExpert Systems with Applications
Issue number8
Publication statusPublished - 15 Jun 2012
Externally publishedYes


  • Friedman test
  • Lazy Learning
  • Long-term forecasting
  • Machine learning
  • Multi-step ahead forecasting
  • NN5 forecasting competition
  • Strategies of forecasting
  • Time series forecasting

Cite this