Iffadah, Adhisa Shilfadianis
Unknown Affiliation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Shapley Additive Explanations Interpretation of the XGBoost Model in Predicting Air Quality in Jakarta Iffadah, Adhisa Shilfadianis; Trimono; Dwi Arman Prasetya
Jurnal Riset Informatika Vol. 7 No. 3 (2025): Juni 2025
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1286.5 KB) | DOI: 10.34288/jri.v7i3.366

Abstract

Air quality degradation has become an increasing global problem since 2008, including in Jakarta. By 2024, air pollution in Jakarta is estimated to cause 8,400 deaths and losses of around 34 billion rupiah. To address air pollution, air quality prediction is needed using historical data of Jakarta Air Quality Index from January 2021 to May 2024. The XGBoost ensemble model was chosen for its ability to handle complex data and prevent overfitting. And Shapley Additive Explanations (SHAP) to understand how the model makes decisions. Results showed the XGBoost model achieved MAPE 4.44%. Analysis with Shapley Additive Explanations (SHAP) identified PM2.5 was significantly affected by max and PM10 features, while O3, CO, SO2, and NO2 remained relevant. An increase in PM10 tends to increase PM2.5 concentrations, suggesting the need to control this parameter to improve air quality. These results are important to provide a better understanding of the dynamics of air quality as well as provide a reference for the government in formulating more effective policies or preventive measures in Jakarta.