Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal EKONOMIS : Journal of Economics and Business Limits: Journal of Mathematics and Its Applications
Septiani, Adeline Vinda
Unknown Affiliation
Computer Science & IT Economics, Econometrics & Finance Mathematics

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Perbandingan Metode GARCH, LSTM, GRU, dan CNN pada Peramalan Volatilitas Kurs Septiani, Adeline Vinda; Afendi, Farit Mochamad; Kurnia, Anang
Limits: Journal of Mathematics and Its Applications Vol. 22 No. 1 (2025): Limits: Journal of Mathematics and Its Applications Volume 22 Nomor 1 Edisi Ma
Publisher : Pusat Publikasi Ilmiah LPPM Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/limits.v22i1.3384

Abstract

Currency volatility is an important aspect of time series data analysis in economics and finance. This study aims to compare the performance of four methods: Generalized Autoregressive Conditional Heteroscedasticity (GARCH), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Convolutional Neural Network (CNN), in predicting the volatility of the Rupiah against the US Dollar. The data used is daily exchange rates from January 2015 to March 2024. The evaluation is conducted by calculating the Root Mean Square Error (RMSE) and the percentage of actual values within a 95% confidence interval on training and testing data. The results indicate that LSTM achieves the lowest RMSE, with values of 5.30E-05 on training data and 2.50E-05 on testing data, demonstrating high accuracy in capturing non-linear patterns and long-term fluctuations. GRU records the highest percentage of actual values within the confidence interval, at 90.32% for training data and 91.72% for testing data, reflecting superior consistency compared to other methods. Meanwhile, GARCH shows competitive performance but lacks robustness on testing data. CNN exhibits the lowest performance, with high RMSE and a low percentage of data within the confidence interval. Overall, GRU emerges as the best method, offering an optimal balance between predictive accuracy and consistency, making it a reliable tool for modeling exchange rate volatility in high-volatility scenarios. Consequently, GRU is utilized for forecasting exchange rate volatility for the next 30 days. These findings contribute to the selection of appropriate methods for modeling exchange rate volatility, particularly amidst global market uncertainty.
Pemodelan ARIMA-GARCH dalam Peramalan Kurs Rupiah Terhadap Yen dengan Masalah Keheterogenan Ragam Meilania, Gusti Tasya; Septiani, Adeline Vinda; Erianti, Efita; Notodiputro, Khairil Anwar; Angraini, Yeni
Ekonomis: Journal of Economics and Business Vol 8, No 1 (2024): Maret
Publisher : Universitas Batanghari Jambi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33087/ekonomis.v8i1.1294

Abstract

The currency exchange rate is the price of a country's currency expressed into another country's currency. At the beginning of 2020, the COVID-19 pandemic affected the weakening and changes in the Rupiah exchange rate against hard currencies, one of which was the Japanese Yen. This affects the expectations of LCS cooperation between Indonesia and Japan in terms of increasing the value of trade to investment between the two countries. Therefore, forecasting the upcoming currency exchange rate is indispensable to determine the upcoming macroeconomic policy. ARIMA is a commonly used quantitative method to forecast future data using past data patterns. The weakness of this method arises when the data violates the assumption of homogeneity of variety that often occurs in financial data, one of which is currency exchange rate data. The ARCH/GARCH model is an effective model for data with uncertain diversity characteristics. However, there is potential to combine ARIMA and ARCH/GARCH into an ARIMA-ARCH/GARCH hybrid model to obtain forecasting results with greater accuracy. In this study, the minimum return data on the Indonesian Rupiah (IDR) exchange rate against the Japanese Yen (JPY) shows the results that the ARIMA(0,0,1) model provides RMSE accuracy of 0.008. While the best forecasting model that can be used to forecast the maximum return data of the IDR exchange rate against JPY is ARIMA(1,0,0)-GARCH(1,1) with a small RMSE accuracy of 0.014. The forecasting results for the minimum return data for buying and selling are expected to strengthen the exchange rate. Meanwhile, the forecasting results for the maximum return data for buying and selling are expected to experience exchange rate weakening.
Co-Authors Anang Kurnia Angraini, Yeni Erianti, Efita Farit Mochamad Afendi Meilania, Gusti Tasya