PENGEMBANGAN MODEL PREDIKSI NILAI PERTUMBUHAN GDP INDONESIA MENGGUNAKAN ALGORITMA MACHINE LEARNING

SETIAWAN, MUHAMMAD IKHSAN and Passarella, Rossi (2025) PENGEMBANGAN MODEL PREDIKSI NILAI PERTUMBUHAN GDP INDONESIA MENGGUNAKAN ALGORITMA MACHINE LEARNING. Undergraduate thesis, Sriwijaya University.

Preview	Image RAMA_56201_09011282126103_cover.jpg - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011282126103.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011282126103_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011282126103_0011067806_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (864kB)
	Text RAMA_56201_09011282126103_0011067806_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (405kB) | Request a copy
	Text RAMA_56201_09011282126103_0011067806_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (553kB) | Request a copy
	Text RAMA_56201_09011282126103_0011067806_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (760kB) | Request a copy
	Text RAMA_56201_09011282126103_0011067806_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (129kB) | Request a copy
	Text RAMA_56201_09011282126103_0011067806_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (203kB) | Request a copy
	Text RAMA_56201_09011282126103_0011067806_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (341kB) | Request a copy

Abstract

Accurate prediction of Gross Domestic Product (GDP) growth is essential for guiding effective economic policymaking in Indonesia. This study proposes a hybrid forecasting approach that integrates fuzzy logic and machine learning to improve the accuracy of GDP growth prediction. Using annual macroeconomic data from 1970 to 2023, we developed 19 input features, combining numerical indicators with fuzzy-based representations and a Non-Stationary Fuzzy Time Series (NSFTS) forecast label. Six machine learning models were evaluated, with Random Forest consistently achieving the lowest mean absolute error (MAE) and the highest accuracy in predicting GDP growth for 2023 (99.45%), outperforming all other models. These results demonstrate the superior ability of Random Forest in capturing short-term economic trends. The proposed approach offers practical value for government agencies and policymakers by enabling data-driven economic planning, improving fiscal policy decisions, and supporting early intervention strategies to stabilize growth. This research affirms the potential of hybrid fuzzy–machine learning frameworks as robust tools for macroeconomic forecasting in emerging economies.

Item Type:	Thesis (Undergraduate)
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Muhammad Ikhsan Setiawan
Date Deposited:	11 Sep 2025 04:38
Last Modified:	11 Sep 2025 04:38
URI:	http://repository.unsri.ac.id/id/eprint/183842

Actions (login required)

View Item