Cleaned Dataset for Predicting Smart City Development Index in Indonesia (2019–2021)

This dataset supports the study "Machine Learning-Based Prediction of Smart City Development Index in Indonesia." It contains lightly pre-processed indicators from 98 cities and regencies across Indonesia between 2019 and 2021. Data was collected from official sources such as BPS-Statistics Indonesia and regional open data portals. It includes 17 variables relevant to smart city dimensions, covering aspects such as economy, infrastructure, education, public health, and access to services. The dataset has undergone basic preprocessing in the form of missing value imputation only. No normalization, transformation, or feature engineering has been applied. This dataset is intended for reproducible machine learning research and urban analytics. It is released under the CC BY 4.0 license.