Purchase - $5.00 NBER Subscribers Download

Machine Learning from Schools About Energy Efficiency

50 Pages Posted: 9 Oct 2017  

Fiona Burlig

University of Chicago

Christopher R. Knittel

Massachusetts Institute of Technology (MIT) - Sloan School of Management; National Bureau of Economic Research (NBER)

David Rapson

University of California, Davis

Mar Reguant

Northwestern University - Department of Economics

Catherine D. Wolfram

University of California, Berkeley - Economic Analysis & Policy Group; National Bureau of Economic Research (NBER)

Date Written: October 2017

Abstract

In the United States, consumers invest billions of dollars annually in energy efficiency, often on the assumption that these investments will pay for themselves via future energy cost reductions. We study energy efficiency upgrades in K-12 schools in California. We develop and implement a novel machine learning approach for estimating treatment effects using high-frequency panel data, and demonstrate that this method outperforms standard panel fixed effects approaches. We find that energy efficiency upgrades reduce electricity consumption by 3 percent, but that these reductions total only 24 percent of ex ante expected savings. HVAC and lighting upgrades perform better, but still deliver less than half of what was expected. Finally, beyond location, school characteristics that are readily available to policymakers do not appear to predict realization rates across schools, suggesting that improving realization rates via targeting may prove challenging.

Institutional subscribers to the NBER working paper series, and residents of developing countries may download this paper without additional charge at www.nber.org.

Suggested Citation

Burlig, Fiona and Knittel, Christopher R. and Rapson, David and Reguant, Mar and Wolfram, Catherine D., Machine Learning from Schools About Energy Efficiency (October 2017). NBER Working Paper No. w23908. Available at SSRN: https://ssrn.com/abstract=3049732

Fiona Burlig (Contact Author)

University of Chicago ( email )

5757 S. University Ave
Chicago, IL 60637
United States

Christopher R. Knittel

Massachusetts Institute of Technology (MIT) - Sloan School of Management ( email )

100 Main Street
E62-416
Cambridge, MA 02142
United States

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

David Rapson

University of California, Davis ( email )

One Shields Avenue
Davis, CA 95616
United States

Mar Reguant

Northwestern University - Department of Economics ( email )

2001 Sheridan Rd
Evanston, IL 60208
United States

Catherine Wolfram

University of California, Berkeley - Economic Analysis & Policy Group ( email )

Berkeley, CA 94720
United States

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Paper statistics

Downloads
13
Abstract Views
60