Working Paper: NBER ID: w30467
Authors: Peter Christensen; Paul Francisco; Erica Myers; Hansen Shao; Mateus Souza
Abstract: Building energy efficiency has been a cornerstone of greenhouse gas mitigation strategies for decades. However, impact evaluations have revealed that energy savings typically fall short of engineering model forecasts that currently guide funding decisions. This creates a resource allocation problem that impedes progress on climate change. Using data from the largest U.S. energy efficiency program, we demonstrate that a data-driven approach to predicting retrofit impacts based on previously realized outcomes is more accurate than the status quo engineering models. Targeting high-return interventions based on these predictions dramatically increases net social benefits, from $0.93 to $1.23 per dollar invested.
Keywords: energy efficiency; climate policy; machine learning; cost-effectiveness; net present benefits
JEL Codes: H50; Q4
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| ML-based predictions of energy consumption (Q47) | actual consumption (D12) |
| improved targeting (via ML predictions) (C45) | increased cost-effectiveness (D61) |
| accurate estimation of NPB (C13) | increased cost-effectiveness (D61) |
| ML model (C52) | predicting energy usage (Q47) |