Optimizing Smart City Strategies: A Data-Driven Analysis Using Random Forest and Regression Analysis

This study investigates the critical factors influencing smart city program success through a comprehensive data-driven analysis of 140 urban centers. Advanced machine learning techniques, specifically random forest algorithms, in conjunction with regression analysis, were employed to examine the correlations between 45 distinct attributes and respective smart city rankings. The findings reveal that the human development index (HDI) is a key predictor of smart city performance. Furthermore, the regression analysis revealed that elements such as education, healthcare, infrastructure, and digital services significantly enhance achieving higher HDI scores. Similarly, factors like education, sanitation, healthcare, and government transparency are closely associated with successfully implementing sharing platforms. These findings highlight the importance of investing in human capital, developing digital infrastructure, and promoting community engagement to create sustainable and resilient smart cities. Policymakers can utilize these findings to prioritize investments and devise effective strategies to improve their city’s ranking.