The identification of smart cities remains a persistent challenge in urban research because city performance depends on the interaction of infrastructure quality, technological service delivery, governance capacity, and resident experience. This paper presents a structured, data-driven framework for classifying smart cities using artificial intelligence, with explicit relevance for urban development policy and comparative city assessment. The empirical design covers 200 cities worldwide and operationalizes smartness through 39 binary indicators organized under two pillars—Structures (n = 19) and Technologies (n = 20)—across five urban domains: health and safety, mobility, activities, opportunities, and governance. The dataset combines resident-based survey evidence for 147 cities, using 120 respondents per city, with documentary coding from online sources for 53 additional cities. Indicator values are converted into binary form using a 50% threshold, and cities exceeding 20 positive indicators are classified as smart. Four machine-learning classifiers—Artificial Neural Network (ANN), Random Forest (RF), Support Vector Machine (SVM), and XGBoost (XGB)—are evaluated on an 80/20 train–test split. The reported comparative accuracy profile shows strong predictive performance across all models, with ANN and RF reaching 97.5%, XGB 97.0%, and SVM 95.0%. Detailed test-set classification reports further indicate that RF and XGB achieve 0.97 accuracy, while ANN and SVM each achieve 0.95. Across the 200-city benchmark, 120 cities (60%) are classified as smart and 80 (40%) as non-smart. Feature-importance analysis shows that smart-city identification is most consistently associated with technological integration, transparent governance, resident feedback mechanisms, public-service digitization, sustainable waste management, and mobility efficiency. The findings demonstrate that artificial intelligence can provide a robust and interpretable framework for identifying smart cities and for informing urban planning, service modernization, and governance reform.