PREDIKSI NILAI TUKAR MATA UANG TERHADAP DOLAR AS MENGGUNAKAN MODEL ARIMA-NGARCH

Novangga, Lydia Almira Rahma (2025) PREDIKSI NILAI TUKAR MATA UANG TERHADAP DOLAR AS MENGGUNAKAN MODEL ARIMA-NGARCH. Undergraduate thesis, Universitas Pembangunan Nasional "Veteran" Jawa Timur.

	Text (Cover) 21083010119_Cover.pdf Download (13MB)
	Text (Bab 1) 21083010119_Bab 1.pdf Download (240kB)
	Text (Bab 2) 21083010119_Bab 2.pdf Restricted to Repository staff only until 25 July 2028. Download (518kB)
	Text (Bab 3) 21083010119_Bab 3.pdf Restricted to Repository staff only until 25 July 2028. Download (589kB)
	Text (Bab 4) 21083010119_Bab 4.pdf Restricted to Repository staff only until 25 July 2028. Download (2MB)
	Text (Bab 5) 21083010119_Bab 5.pdf Restricted to Repository staff only until 25 July 2028. Download (284kB)
	Text (Daftar Pustaka) 21083010119_Daftar Pustaka.pdf Download (195kB)
	Text (Lampiran) 21083010119_Lampiran.pdf Restricted to Repository staff only until 25 July 2028. Download (441kB)

Abstract

Currency exchange rate movements against the US dollar in ASEAN countries are an important factor affecting economic stability, international trade, and monetary policy. Unpredictable exchange rate fluctuations pose a serious challenge to fiscal strategy formulation, international capital flows, and investment decision-making. In this context, a predictive model is needed that not only captures historical data patterns but also maps the dynamics of market volatility, which is heteroskedastic and asymmetric. The main issue in this research is the limited ability of linear models such as ARIMA to handle volatility instability. As a solution, this study adopts a combined ARIMA-NGARCH model approach to predict the exchange rates of three major currencies IDR, MYR, and SGD against the USD. The ARIMA model is used to estimate the linear components of log-returns, while the NGARCH model is used to capture the non-linear dynamics of residual volatility. This study uses daily exchange rate data from Yahoo Finance for the period from August 2019 to August 2024. The urgency of this study lies in the need for more flexible and accurate predictive models amid high global uncertainty. Previous research has been limited to a single currency or has only used the standard GARCH model, which assumes symmetry. Therefore, the innovation of this study is the comparative application of the ARIMA-NGARCH model to three currencies simultaneously, as well as the development of a Streamlit-based user interface to present prediction results in an interactive and practical manner. This study aims to apply and evaluate the ARIMA-NGARCH model in predicting the exchange rates of three ASEAN currencies against the USD, as well as to build an interactive user interface to facilitate access to analysis results and prediction simulations.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Trimono, Trimono	NIDN0008099501	trimono.stat@upnjatim.ac.id
Thesis advisor	Hindrayani, Kartika Maulida	NIDN0009099205	kartikamaulida.ds@upnjatim.ac.id

Subjects:

H Social Sciences > HA Statistics
Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Lydia Almira Rahma Novangga

Date Deposited:

28 Jul 2025 07:22

Last Modified:

28 Jul 2025 07:23

URI:

https://repository.upnjatim.ac.id/id/eprint/40865