FORESIGHT, Issue 57

Description

Spring 2020

Special Feature

Will Deep and Machine Learning Solve Our Forecasting Problems? by Stephan Kolassa
Many of the methods competing in the M4 competition made use of machine learning (ML) models, further stimulating interest in the application of ML for forecasting but also raising important caveats. Foresight Associate Editor Stephan Kolassa provides a needed perspective on the potential of ML forecasting models.

• Book Review by Stephan Kolassa
  Rebooting AI: Building Artificial Intelligence We Can Trust by Gary Marcus and Ernest Davis

Articles

1. The Economic/Energy/Environmental Conundrum with Official Projections to 2050 by Ira Sohn
   Barring miraculous technological developments to accelerate the decarbonization of the world’s energy system over the next 30 years, political leaders will have to “choose their poison”: that is, faster economic growth and higher emissions or lower economic growth and fewer emissions.
2. Developing a Modern Retail Forecasting System: People and Processes by Phillip Yelland and Zeynep Erkin Baz
   In the first installment of this three-part series, as technical leads in the Data Science/AI team at U.S. retailer Target, we described the overall architecture and design of a demand forecasting system capable of efficiently generating the nearly one billion weekly forecasts required for Target’s operations. In this second article, we recount some of the lessons learned in the process of developing and implementing the forecasting system.
3. The M4 Forecasting Competition: Takeaways for the Practitioner by Michael Gilliland
   The article provides background history and motivation for the M4, competition results, and important takeaways for business forecasting practitioners.

   • Commentary: The M4 Competition and a Look to the Future by Fotios Petropoulos

4. Forecaster in the Field
   This issue’s Forecaster in the Field features Tim Januschowski, Manager of Machine Learning Science at AWS. Tim calls for closer collaboration among the forecasting, ML, and OR communities to build better forecasting models, improving their empirical rigor, scalability, downstream implications, and software frameworks.