Machine Learning Models for Predicting the Air Quality Index in Hanoi, Jakarta, and Bangkok

The environment plays a crucial role in the survival of living beings, with air quality being a key factor affecting health and ecosystems. Clean air must be free from pollution that can disrupt the environmental balance. In Southeast Asia, the three cities with the highest levels of air pollution are Hanoi, Jakarta, and Bangkok. This study aims to evaluate the accuracy of air quality prediction models in these cities using two machine learning algorithms, namely Support Vector Machine and eXtreme Gradient Boosting, optimized with GridSearch Cross-Validation and the Synthetic Minority Over-sampling Technique. The primary focus of this research is to measure model accuracy and identify the most influential pollutant compounds. The results indicate that eXtreme Gradient Boosting achieved 100% accuracy in predicting air quality even without hyperparameter optimization and oversampling.