Machine learning reduces soft costs for residential solar photovoltaics

Changgui Dong; Gregory Nemet; Xue Gao; Galen Barbose; Benjamin Sigrin; Eric O'Shaughnessy

doi:10.1038/s41598-023-33014-4

Machine learning reduces soft costs for residential solar photovoltaics

Sci Rep. 2023 May 3;13(1):7213. doi: 10.1038/s41598-023-33014-4.

Authors

Changgui Dong¹, Gregory Nemet², Xue Gao^{3

4}, Galen Barbose⁵, Benjamin Sigrin⁶, Eric O'Shaughnessy⁷

Affiliations

¹ School of Public Administration and Policy, Renmin University of China, Beijing, 100872, China. changgui.dong@ruc.edu.cn.
² La Follette School of Public Affairs, University of Wisconsin-Madison, Madison, WI, 53706, USA.
³ Department of Political Science, University of Miami, Coral Gables, FL, 33146, USA. xgao5@fsu.edu.
⁴ Askew School of Public Administration and Policy, Florida State University, Tallahassee, FL, 32306, USA. xgao5@fsu.edu.
⁵ Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA.
⁶ National Renewable Energy Laboratory, Golden, CO, 80401, USA.
⁷ Clean Kilowatts, LLC, Boulder, CO, 80302, USA.

Abstract

Further deployment of rooftop solar photovoltaics (PV) hinges on the reduction of soft (non-hardware) costs-now larger and more resistant to reductions than hardware costs. The largest portion of these soft costs is the expenses solar companies incur to acquire new customers. In this study, we demonstrate the value of a shift from significance-based methodologies to prediction-oriented models to better identify PV adopters and reduce soft costs. We employ machine learning to predict PV adopters and non-adopters, and compare its prediction performance with logistic regression, the dominant significance-based method in technology adoption studies. Our results show that machine learning substantially enhances adoption prediction performance: The true positive rate of predicting adopters increased from 66 to 87%, and the true negative rate of predicting non-adopters increased from 75 to 88%. We attribute the enhanced performance to complex variable interactions and nonlinear effects incorporated by machine learning. With more accurate predictions, machine learning is able to reduce customer acquisition costs by 15% ($0.07/Watt) and identify new market opportunities for solar companies to expand and diversify their customer bases. Our research methods and findings provide broader implications for the adoption of similar clean energy technologies and related policy challenges such as market growth and energy inequality.