Shapley Additive Explanations Interpretation of the XGBoost Model in Predicting Air Quality in Jakarta

Adhisa Shilfadianis Iffadah; Trimono; Dwi Arman Prasetya

doi:10.34288/jri.v7i3.366

Authors

Adhisa Shilfadianis Iffadah UPN Veteran Jawa Timur
Trimono UPN Veteran Jawa Timur
Dwi Arman Prasetya UPN Veteran Jawa Timur

(*) Corresponding Author

DOI:

https://doi.org/10.34288/jri.v7i3.366

Keywords:

Prediction, Interpretation, XGBoost, Shapley Additive Explanations, Air quality

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.

Downloads

Download data is not yet available.

References

Agatha. 2023. “Apa Itu Indeks Kualitas Udara (AQI) Dan Bagaimana Cara Menggunakannya?” Ai Care .

Astutiningsih, Tiyas, Dewi Retno Sari Saputro, and Sutanto. 2023. “Optimasi Algoritme Xtreme Gradient Boosting (XGBoost) Pada Harga Saham PT. United Tractors Tbk.” SPECTA Journal of Technology 7(3):632–41. doi: 10.35718/specta.v7i3.1031.

BBC News Indonesia. 2023. “Riset Sebut Polusi Udara PLTU Suralaya Banten ‘Menyebabkan 1.470 Nyawa Melayang.’” BBC.

Damaliana, Aviolla Terza, Amri Muhaimin, and Dwi Arman Prasetya. 2024. “FORECASTING THE OCCUPANCY RATE OF STAR HOTELS IN BALI USING THE XGBOOST AND SVR METHODS.” doi: 10.14710/JSUNIMUS.

Faqihah Muharroroh Itsnaini. 2024. “Kemenkes: Polusi Udara Faktor Resiko Kematian Ke-5 Di Indonesia.” Kompas.Com.

Fauzan, Fardhi Dzakwan, Dhymas Adhyza Rayhan, Hala Mutiara Putri, and Fitri Kartiasih. 2024. “Peramalan Konsentrasi PM2.5 Menggunakan Model ARCH/GARCH Dan Long Short-Term Memory (Studi Kasus: Kota Jakarta Pusat).” Infomatek 26(1):27–44. doi: 10.23969/infomatek.v26i1.12603.

Jange, Beno. 2022. “Prediksi Harga Saham Bank BCA Menggunakan XGBoost.” ARBITRASE: Journal of Economics and Accounting 3(2):231–37. doi: 10.47065/arbitrase.v3i2.495.

Khusna, Nida Faoziatun, Syifa Aulia, Shinta Amaria, Alfidha Rahmah, Safril Ahmadi Sanmas, and Fatkhurokhman Fauzi. 2023. “Peramalan Kualitas Udara Di Semarang Menggunakan Metode Autoregressive Integrated Moving Average (ARIMA) Forecasting Air Quality in Semarang Using the Autoregressive Integrated Moving Average (ARIMA) Method.” Prosiding Seminar Nasional UNIMUS 6.

Kothandaraman, D., N. Praveena, K. Varadarajkumar, B. Madhav Rao, Dharmesh Dhabliya, Shivaprasad Satla, and Worku Abera. 2022. “Intelligent Forecasting of Air Quality and Pollution Prediction Using Machine Learning.” Adsorption Science & Technology 2022. doi: 10.1155/2022/5086622.

Kurniawan, Wildan, and Uce Indahyanti. 2024. “Prediksi Angka Harapan Hidup Penduduk Menggunakan Metode XGBoost.” Indonesian Journal of Applied Technology 1(2):18. doi: 10.47134/ijat.v1i2.3045.

Liu, Bing, Xianghua Tan, Yueqiang Jin, Wangwang Yu, and Chaoyang Li. 2021. “Application of RR-XGBoost Combined Model in Data Calibration of Micro Air Quality Detector.” Scientific Reports 11(1):15662. doi: 10.1038/s41598-021-95027-1.

Luo, Junling, Zhongliang Zhang, Yao Fu, and Feng Rao. 2021. “Time Series Prediction of COVID-19 Transmission in America Using LSTM and XGBoost Algorithms.” Results in Physics 27. doi: 10.1016/j.rinp.2021.104462.

Maricar, Azman. 2019. “Analisa Perbandingan Nilai Akurasi Moving Average Dan Exponential Smoothing Untuk Sistem Peramalan Pendapatan Pada Perusahaan XYZ.” Jurnal Sistem Dan Informatika.

Nababan, Adli A., Miftahul Jannah, Mia Aulina, and Dwiki Andrian. 2023a. “PREDIKSI KUALITAS UDARA MENGGUNAKAN XGBOOST DENGAN SYNTHETIC MINORITY OVERSAMPLING TECHNIQUE (SMOTE) BERDASARKAN INDEKS STANDAR PENCEMARAN UDARA (ISPU).” JTIK (Jurnal Teknik Informatika Kaputama) 7(1):214–19. doi: 10.59697/jtik.v7i1.66.

Nababan, Adli A., Miftahul Jannah, Mia Aulina, and Dwiki Andrian. 2023b. “PREDIKSI KUALITAS UDARA MENGGUNAKAN XGBOOST DENGAN SYNTHETIC MINORITY OVERSAMPLING TECHNIQUE (SMOTE) BERDASARKAN INDEKS STANDAR PENCEMARAN UDARA (ISPU).” JTIK (Jurnal Teknik Informatika Kaputama) 7(1). doi: 10.59697/jtik.v7i1.66.

Pan, Bingyue. 2018. “Application of XGBoost Algorithm in Hourly PM2.5 Concentration Prediction.” in IOP Conference Series: Earth and Environmental Science. Vol. 113. Institute of Physics Publishing.

Putra, I. Kadek Pasek Kusuma Adi, Sediono, M. Fariz Fadillah Mardianto, and Elly Pusporani. 2024. “Analisis Prediktif Menggunakan Metode Hybrid Seasonal Autoregressive Integrated Moving Average – Artificial Neural Network Pada Data Konsentrasi PM2.5 Harian Di DKI Jakarta.” G-Tech: Jurnal Teknologi Terapan 8(1):565–75. doi: 10.33379/gtech.v8i1.3896.

Riyantoko, Prismahardi Aji, Kartika Maulida Hindrayani, Tresna Maulana Fahrudin, and Mohammad Idhom. 2021. Exploratory Data Analysis and Machine Learning Algorithms to Classifying Stroke Disease. Vol. 2.

Riyantoko, Prismahardi Aji, Kartika Maulida Hindrayani, Tresna Maulana Fahrudin, and Eristya Maya Safitri. 2020. Southeast Asia Happiness Report in 2020 Using Exploratory Data Analysis. Vol. 2.

Salsabilla, Shafira, Amadea Fitri Syaharani, and Nur Chamidah. 2023. “Prediction of PM2.5 in DKI Jakarta Using Ordinary Kriging Method.” Enthusiastic : International Journal of Applied Statistics and Data Science 48–58. doi: 10.20885/enthusiastic.vol3.iss1.art5.

Statistika, Departemen, Fakultas Sains, Dan Matematika, Universitas Diponegoro, Jl Soedarto, and S. H. Tembalang. 2017. Valuasi Harga Saham PT Aneka Tambang Tbk Sebagai Peraih IDX Best Blue 2016 TRIMONO, DI ASIH I MARUDDANI. Vol. 17.

Trimono, Trimono, Abdulah Sonhaji, and Utriweni Mukhaiyar. 2020. “FORECASTING FARMER EXCHANGE RATE IN CENTRAL JAVA PROVINCE USING VECTOR INTEGRATED MOVING AVERAGE.” MEDIA STATISTIKA 13(2):182–93. doi: 10.14710/medstat.13.2.182-193.