Passive over active: How low-cost strategies influence urban energy equity

•Using XGBoost, Neural Network, and Linear Regression to Predict Energy Burden.•Predicting the Average Energy Burden with 94.8 % Accuracy.•Passive Design Factors significantly reduce energy costs compared to active design.•Geographic location plays a vital role in the energy burden on households. This study delves into the energy burden on households, a crucial aspect of energy justice, influenced by urban environment factors and buildings’ passive and active designs. It evaluates the effects of passive and active design features on household energy expenditures at the census tract scale. Applying advanced Machine Learning techniques, including multiple and decision tree regressions, random forests, support vector machines, XGBoost, and Neural Networks, the research assesses the impact of various factors on the energy burden. Findings reveal that passive design elements significantly outweigh active ones in reducing energy costs at the urban scale, as confirmed by a model with a 94.8 % R2 accuracy. The insights provided are vital for policymakers, urban planners, architects, and researchers, pushing for sustainable urban planning and energy justice by prioritizing effective design strategies. This contributes to a broader understanding and implementation of energy-efficient measures in urban development.