Comparison of Ordinal Logistic Regression, XGBoost, and TabNet Models for Air Quality Classification in Jakarta City

This study aims to compare the performance of statistical, machine learning, and deep learning models in solving the air quality classification problem in Jakarta province over the period from 2018 to 2024. The dataset used in this research was obtained from the ‘Satu Data Indonesia’ website, specifically the daily air quality data ISPU (Indeks Standar Pencemar Udara). Specifically, the models evaluated in this study include Ordinal Logistic Regression, XGBoost, and TabNet, and their performance is assessed using several evaluation metrics, such as precision, recall, F1-score, and accuracy. The research process is divided into several stages, including hyperparameter tuning, to enhance model performance. The dataset consists of daily air quality data, with variables such as PM₁₀, SO₂, CO, O₃, and NO₂. The results indicate that the XGBoost model outperforms the other models.