Stacking Ensemble Berbasis Optimasi Hyperparameter pada Peramalan Indeks Standar Pencemar Udara Kota Jakarta

Taqiyuddin, Fahmi Hammam (2026) Stacking Ensemble Berbasis Optimasi Hyperparameter pada Peramalan Indeks Standar Pencemar Udara Kota Jakarta. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 22083010026.-cover.pdf Download (1MB)
	Text (Bab 1) 22083010026.-bab 1.pdf Download (250kB)
	Text (bab 2) 22083010026.-bab 2.pdf Restricted to Repository staff only until 14 July 2029. Download (827kB) \| Request a copy
	Text (Bab 3) 22083010026.-bab 3.pdf Restricted to Repository staff only until 14 July 2029. Download (435kB) \| Request a copy
	Text (Bab 4) 22083010026.-bab 4.pdf Restricted to Repository staff only until 14 July 2029. Download (1MB) \| Request a copy
	Text (Bab 5) 22083010026.-bab 5.pdf Download (225kB)
	Text (Daftar Pustaka) 22083010026.-daftarpustaka.pdf Download (184kB)
	Text (Lampiran) 22083010026.-lampiran.pdf Restricted to Repository staff only Download (473kB) \| Request a copy

Abstract

Air pollution is still an environmental problem that has an impact on public health and urban quality of life. The State of Global Air 2024 report shows that air pollution contributed to about 8.1 million global deaths in 2021. In Jakarta, air pollution is estimated to cause more than 10,000 deaths and health losses that amount to billions of dollars each year. This study aims to build a prediction model of the Jakarta City Air Pollution Standard Index (ISPU) using the Stacking Ensemble architecture that combines Random Forest and XGBoost as the base learner and Ridge Regression as the meta learner. To improve model performance, hyperparameter optimization is applied using Bayesian Optimization and Genetic Algorithm. The research data uses daily air quality data for the City of Jakarta for the 2023–2025 period obtained from the One Data Jakarta portal. The results showed that both optimization methods were able to improve the performance of the model compared to Baseline, which was shown by the decrease in RMSE values from 17.7586 to 16.7993 in Bayesian Optimization and 16.7869 in the Genetic Algorithm, as well as the increase in R² values from 0.2546 to 0.3330 and 0.3362. The best model is then implemented into a Streamlit-based dashboard to present ISPU forecasting results interactively.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Damaliana, Aviolla Terza	NIDN0002089402	aviolla.terza.sada@upnjatim.ac.id
Thesis advisor	Adziima, Andri Fauzan	NUPTK9844773674130292	andri.fauzan.fasilkom@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Fahmi Taqiyuddin

Date Deposited:

14 Jul 2026 06:24

Last Modified:

14 Jul 2026 07:09

URI:

https://repository.upnjatim.ac.id/id/eprint/55346