In the context of rising environmental challenges, assessing lifestyle sustainability has become a pivotal area of research. This study leverages a novel dataset—Lifestyle Sustainability Data—to explore sustainability metrics using exploratory data analysis (EDA) and machine learning techniques. The dataset encompasses critical parameters such as electricity consumption, water usage, and environmental awareness, which collectively inform the sustainability rating for individuals or households. EDA revealed significant trends and patterns, highlighting correlations among sustainability factors. It provided insights into the consumption behaviours that influence environmental impact. Subsequently, a Random Forest algorithm was employed to calculate sustainability ratings, effectively capturing the interplay between the variables. This machine learning approach not only facilitated accurate predictions but also offered feature importance metrics, which underscored the relative contributions of different factors to the overall sustainability score. The results indicate that environmental awareness plays a significant role in moderating consumption patterns, with households demonstrating higher awareness exhibiting lower electricity and water usage. Additionally, Random Forest's robust performance in handling complex, non-linear relationships reinforced its suitability for sustainability analysis. This research underscores the importance of combining data analytics and machine learning to quantify and promote sustainable lifestyles. The findings provide actionable insights for policymakers, utility companies, and environmental advocates aiming to encourage sustainable consumption behaviours.
Volume 17 | Issue 2
Pages: 38-46