Foreword and editorial

  1. “Foreword to the M4 Competition” by Nassim Nicholas Taleb
  2. “The M4 competition: Bigger. Stronger. Better.” by Fotios Petropoulos and Spyros Makridakis

 

Background and main paper

  1. “A brief history of forecasting competitions” by Rob Hyndman
  2. “Forecasting in social settings: the state of the art” by Spyros Makridakis, Rob Hyndman & Fotios Petropoulos
  3. “Predicting/Hypothesizing the findings of the M4 Competition” by Evangelos Spiliotis, Spyros Makridakis & Vassilios Assimakopoulos
  4. “Are forecasting competitions data representative of the reality?” by Evangelos Spiliotis, Andreas Kouloumos, Vassilios Assimakopoulos & Spyros Makridakis
  5. “The M4 competition: 100,000 time series and 61 forecasting methods” by Spyros Makridakis, Evangelos Spiliotis & Vassilios Assimakopoulos

 

Winning methods and approaches

  1. “A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting” by Slawek Smyl
  2. “FFORMA: Feature-based Forecast Model Averaging” by Pablo Montero-Manso, George Athanasopoulos, Rob Hyndman & Thiyanga Talagala
  3. “Weighted Ensemble of Statistical Models” by Maciej Pawlikowski, Agata Chorowska & Olena Yanchuk
  4. “Combination-based forecasting method: M4 competition” by Srihari Jaganathan & Prakash Prakash
  5. “GROEC: Combination method via Generalized Rolling Origin Evaluation” by Jose Augusto Fiorucci & Francisco Louzada
  6. “A Simple Combination of Univariate Models” by Fotios Petropoulos & Ivan Svetunkov
  7. “Fast and Accurate Yearly Time Series Forecasting with Forecast Combinations” by David Shaub
  8. “Correlated daily time series and forecasting in the M4 competition” by Anti Ingel, Novin Shahroudi, Markus Kangsepp, Andre Tattar, Viacheslav Komisarenko & Meelis Kull
  9. “Card forecasts for M4” by Jurgen Doornik, Jennie Castle & David Hendry
  10. “Forecasting the M4 Competition Weekly Data: Forecast Pro’s Winning Approach” by Sarah Darin & Eric Stellwagen

 

Discussion papers

  1. “Why Do Some Combinations Perform Better Than Others?” by Kenneth Lichtendahl & Robert Winkler
  2. “Machine Learning in M4: What Makes a Good Model?” by Jocelyn Barker
  3. “The M4 Forecasting Competition - A Practitioner’s View” by Chris Fry & Michael Brundage
  4. “The Value Added by Machine Learning Approaches in Forecasting” by Mike Gilliland
  5. “Criteria for Classifying Forecasting Methods” by Tim Januschowski, Jan Gasthaus, Yuyang Wang, David Salinas, Valentin Flunkert, Michael Bohlke-Schneider & Laurent Callot
  6. “Combining prediction intervals in the M4 competition” by Yael Grushka-Cockayne & Victor Richmond R. Jose

 

Commentaries & rebuttal

  1. “Learning from Forecasting Competitions” by Robert Fildes
  2. “Performance measurement in the M4 Competition: possible future research” by Paul Goodwin
  3. “Forecasting with high frequency data: M4 Competition and beyond” by Tao Hong
  4. “Data Adjustments, Overfitting and Representativeness” by Keith Ord
  5. “Why Does Forecast Combination Work so Well?” by Amir Atiya
  6. “Comments on M4 competition” by Gianluca Bontempi
  7. “On the M4.0 forecasting competition: can you tell a 4.0 earthquake from a 3.0?” by Konstantinos Nikolopoulos, Dimitrios Thomalos, Ilias Katsagounos & Waleed Alghassab
  8. “M4 competition: What’s next?” by Dilek Onkal
  9. “Why the ‘best’ point forecast depends on the error or accuracy measure” by Stephan Kolassa
  10. “Correlation Analysis of Forecasting Methods: The Case of the M4 Competition” by Pantelis Agathangelou, Demetris Trihinas & Ioannis Katakis
  11. “Responses to discussions and commentaries” by Spyros Makridakis, Evangelos Spiliotis & Vassilios Assimakopoulos

 

Conclusions

  1. “The M4 competition: Conclusions” by Spyros Makridakis & Fotios Petropoulos

 

Published by Elsevier B.V. on behalf of the International Institute of Forecasters.