Abstract
As part of the Year of Climate Action, Campus Operations has been looking at ways to make Brandeis more energy efficient. Compared to the large network of institutions of higher education in the Greater Boston Area, research shows that Brandeis has 15% to 20% higher energy use intensity than our neighboring campuses. In order to reduce our electricity consumption, my project seeks to understand the historical and future patterns of energy usage. I synthesized and analyzed five years of electricity data from buildings across campus using Python and Excel, focusing on data cleaning, visualization, and predictive analytics. My research establishes that machine learning, specifically random forest regression, can be used to accurately predict electricity usage for a university campus. On a larger scale, my project demonstrates the ways in which data analytics can be employed in Campus Operations.