Estimasi Value at Risk Pada Nilai Tukar Mata Uang Menggunakan Simulasi Monte Carlo dan Pendekatan ARIMA-GARCH

Gunawan, Elbert Vito (2025) Estimasi Value at Risk Pada Nilai Tukar Mata Uang Menggunakan Simulasi Monte Carlo dan Pendekatan ARIMA-GARCH. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5006211101-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (4MB) | Request a copy

Abstract

Fluktuasi nilai tukar merupakan salah satu risiko utama dalam manajemen keuangan. Penelitian ini bertujuan mengestimasi Value at Risk (VaR) harian pada nilai tukar USD/IDR dan CNY/IDR menggunakan dua pendekatan: Simulasi Monte Carlo dan ARIMA-GARCH. Data yang digunakan berupa data harian dari 1 Januari 2016 hingga 31 Januari 2025. Simulasi Monte Carlo dilakukan dalam dua skenario: asumsi distribusi normal dan fitting distribusi Generalized Lambda Distribution (GLD) sebanyak 10.000 iterasi. Estimasi VaR dari pendekatan distribusi normal pada level 99% menghasilkan nilai sebesar -0.006423 (USD/IDR) dan -0.00688 (CNY/IDR), namun hasil Kupiec Test menunjukkan model ini tidak akurat pada kedua level kepercayaan. Sementara pendekatan GLD menghasilkan VaR yang lebih ekstrem di level 99% yakni -0.00951 (USD/IDR) dan -0.00927 (CNY/IDR), dengan hasil Kupiec Test yang valid hanya di level 99%. Pendekatan ARIMA-GARCH menggunakan model ARIMA(2,0,0)-GARCH(1,1) untuk USD/IDR dan ARIMA(2,0,0)-GARCH(1,1) untuk CNY/IDR. Hasil estimasi VaR-nya adalah -0.00581 (USD/IDR) dan -0.00656 (CNY/IDR) pada level 99%. Berdasarkan Kupiec Test, model ini valid di level 95% tetapi tidak valid di level 99%. Hasil menunjukkan bahwa pendekatan ARIMA-GARCH lebih akurat dalam menangkap risiko harian pada tingkat kepercayaan 95%, sedangkan pendekatan GLD lebih cocok digunakan pada pengukuran risiko ekstrem di level 99%. Temuan ini mendukung pentingnya pemilihan metode estimasi yang disesuaikan dengan karakteristik distribusi dan tingkat kepercayaan yang diinginkan dalam manajemen risiko nilai tukar.
=====================================================================================================================================
Exchange rate fluctuation is one of the main risks in financial management. This study aims to estimate the daily Value at Risk (VaR) for USD/IDR and CNY/IDR exchange rates using two approaches: Monte Carlo Simulation and the ARIMA-GARCH model. The analysis uses daily data from January 1, 2016, to January 31, 2025. Monte Carlo Simulation was conducted under two scenarios: assuming normal distribution and fitting a Generalized Lambda Distribution (GLD), with 10,000 iterations. Under the normal distribution assumption, the 99% VaR values were -0.00643 (USD/IDR) and -0.00688 (CNY/IDR), but Kupiec Test results indicated that this model was invalid at both 95% and 99% confidence levels. In contrast, the GLD-based simulation produced more extreme 99% VaR values: -0.00951 (USD/IDR) and -0.00927 (CNY/IDR), with Kupiec Test validation only at the 99% level. The ARIMA-GARCH approach used ARIMA(2,0,0)-GARCH(1,1) for USD/IDR and ARIMA(2,0,0)-GARCH(1,1) for CNY/IDR. It yielded 99% VaR values of -0.00581 (USD/IDR) and -0.00656 (CNY/IDR). Based on the Kupiec Test, this model was valid at the 95% confidence level but not at 99%. These findings suggest that ARIMA-GARCH is more accurate for capturing daily exchange rate risks at moderate confidence levels, while GLD-based Monte Carlo is more suitable for extreme risk estimation at high confidence levels. The results emphasize the importance of choosing the appropriate method according to the distribution characteristics and desired confidence level in exchange rate risk management.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	ARIMA-GARCH, Kupiec Test, Nilai Tukar, Simulasi Monte Carlo, Value at Risk, ARIMA-GARCH, Exchange Rate, Kupiec Test, Monte Carlo Simulation, Value at Risk
Subjects:	H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA30.3 Time-series analysis H Social Sciences > HG Finance > HG4012 Mathematical models H Social Sciences > HG Finance > HG4529 Investment analysis Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Actuaria > 94203-(S1) Undergraduate Thesis
Depositing User:	Elbert Vito Gunawan
Date Deposited:	30 Jul 2025 07:51
Last Modified:	30 Jul 2025 07:51
URI:	http://repository.its.ac.id/id/eprint/123733

Actions (login required)

View Item