Major
Business Administration
Anticipated Graduation Year
2021
Access Type
Open Access
Abstract
Energy markets worldwide are facing two primary issues: 1) meeting exponentially increasing demand and 2) satisfying external pressures to transition to clean energy sources.
This report studies electricity consumption patterns in the City of Chicago through historical socioeconomic data. Using an unsupervised method of analysis (K-Means Cluster) together with a supervised method (Neural Net), our report provides three classifications of Chicago neighborhoods and identifies the strongest predictors of electricity consumption in each. Using this analysis framework, major cities can effectively devise long-term strategies for meeting energy demand while planning for a sustainable future.
Faculty Mentors & Instructors
Kmet, Carolyn, Senior Lecturer, Quinlan School of Business
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.
Using K-Means Clustering and Neural Net Analysis to Define and Predict Chicago Neighborhood Energy Consumption Trends
Energy markets worldwide are facing two primary issues: 1) meeting exponentially increasing demand and 2) satisfying external pressures to transition to clean energy sources.
This report studies electricity consumption patterns in the City of Chicago through historical socioeconomic data. Using an unsupervised method of analysis (K-Means Cluster) together with a supervised method (Neural Net), our report provides three classifications of Chicago neighborhoods and identifies the strongest predictors of electricity consumption in each. Using this analysis framework, major cities can effectively devise long-term strategies for meeting energy demand while planning for a sustainable future.