PREDIKSI INFLASI HARGA PANGAN MENGGUNAKAN PENDEKATAN MACHINE LEARNING BERBASIS MULTIVARIATE TIME SERIES

GHAZALI, AHMAD ALFARREL and Passarella, Rossi (2025) PREDIKSI INFLASI HARGA PANGAN MENGGUNAKAN PENDEKATAN MACHINE LEARNING BERBASIS MULTIVARIATE TIME SERIES. Undergraduate thesis, Sriwijaya University.

	Image RAMA_56201_09011282126100_cover.jpg - Cover Image Available under License Creative Commons Public Domain Dedication. Download (174kB)
	Text RAMA_56201_09011282126100.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011282126100_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_56201_09011282126100_0011067806_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (864kB)
	Text RAMA_56201_09011282126100_0011067806_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (457kB) | Request a copy
	Text RAMA_56201_09011282126100_0011067806_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011282126100_0011067806_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011282126100_0011067806_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (233kB) | Request a copy
	Text RAMA_56201_09011282126100_0011067806_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (277kB) | Request a copy
	Text RAMA_56201_09011282126100_0011067806_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (434kB) | Request a copy

Abstract

Food price inflation is an important economic indicator that can affect the social and economic stability of a country. This study aims to develop a model for predicting food price inflation in Indonesia using a machine learning approach based on multivariate time series. The data used includes monthly inflation variables as well as market price index data such as opening (open), highest (high), lowest (low), and closing (close) prices, obtained from World Bank. Three machine learning models are utilized in this study: Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM). The evaluation is conducted using the Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Error (MAE) metric on both training/validation and testing phases. The results indicate that the SVR model provides the best performance and consistency compared to LSTM and BiLSTM model. These findings demonstrate that SVR is more effective in handling moderate data complexity with limited data compared to the other models used in this study.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Inflasi Harga Pangan, Prediksi, Machine Learning, Multivariate Time Series
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:	Ahmad Alfarrel Ghazali
Date Deposited:	22 Aug 2025 02:22
Last Modified:	22 Aug 2025 02:22
URI:	http://repository.unsri.ac.id/id/eprint/183162

Actions (login required)

View Item