Small steps with big data: Using machine learning in energy and environmental economics

Matthew C. Harding, Carlos Lamarche

Research output: Contribution to journalReview articlepeer-review

1 Scopus citations


This article reviews recent endeavors to incorporate big data and machine learning techniques into energy and environmental economics research. We find that novel datasets, from high frequency smart meter data to satellite images and social media data, are already used by researchers. At the same time most of the analyses rely on traditional econometric techniques. Nevertheless, we find applications of machine learning models that address the high dimensionality of the data and seek out new and better strategies for estimating heterogenous treatment effects. We provide an introduction to the main themes in machine learning, which are likely to be of use to economists in energy and environmental economics, and illustrate them using a real data example derived from an energy efficiency program evaluation. We provide the data and code in order to stimulate further research in this area.

Original languageEnglish
Pages (from-to)469-488
Number of pages20
JournalAnnual Review of Resource Economics
StatePublished - Oct 5 2021

Bibliographical note

Funding Information:
workshop at the University of Illinois at Urbana-Champaign where this review originated as a keynote talk

Publisher Copyright:
© 2021 by Annual Reviews.All rights reserved.


  • Big data
  • Energy demand
  • Machine learning

ASJC Scopus subject areas

  • Economics and Econometrics


Dive into the research topics of 'Small steps with big data: Using machine learning in energy and environmental economics'. Together they form a unique fingerprint.

Cite this