Machine Learning from Schools about Energy Efficiency
Posted on February 19th, 2019 by tagadminThis working paper studies the effectiveness of energy efficiency upgrades in K-12 schools, and demonstrate that the machine learning method outperforms standard panel fixed effects approaches. The authors find that the upgrades deliver only 53% of ex ante expected savings on average, and find a similarly low correlation between school-specific predictions of energy savings and realized savings.
READ more