Home // International Journal On Advances in Systems and Measurements, volume 17, numbers 3 and 4, 2024 // View article

Regression Model-Based Prediction for Building Energy Star Score of New York City

Authors:
Fan Zhang
Baiyun Chen
Faria Brishti
Sameeruddin Mohammed
Fan Wu
Ling Bai

Keywords: Machine learning; Regression; Data analysis; Model evaluation

Abstract:
Machine learning algorithms have recently shown promise in predicting Energy Star Scores for buildings, outperforming traditional forecasting methods. While previous studies have focused on specific building types, this comprehensive research expands the scope to analyze and predict Energy Star Scores across four diverse building categories in New York City: residential, educational, commercial, and lodging structures. Our study employs rigorous feature engineering and selection to develop nine distinct regression models applied to these four building types. We compare various machine learning algorithms to identify the most effective predictive model for each category. The Gradient Boosting Regressor (GBR) consistently emerges as the top performer across building types, demonstrating superior accuracy and stability in predictions. We provide a detailed analysis of feature importance for each building category, offering insights into the key factors influencing energy efficiency across different sectors. By extending the analysis to multiple building types and employing a range of regression models, this study contributes to a more comprehensive understanding of urban energy efficiency and provides tailored strategies for improving energy performance across New York City's diverse building stock for urban planners, building managers, and policymakers.

Pages: 176 to 188

Copyright: Copyright (c) to authors, 2024. Used with permission.

Publication date: December 30, 2024

Published in: journal

ISSN: 1942-261x