Sa'adah, Nida Atus (2024) Analisis Peramalan Suku Bunga Tabungan Pada Kelompok Bank Persero dengan Menggunakan Metode Autoregressive Moving Average-Generalized Autoregressive Conditional Heteroskedasticity (ARIMA-GARCH). Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5002201030_Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5002201030_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (3MB) | Request a copy |
Abstract
Suku bunga tabungan adalah persentase tertentu dari saldo tabungan yang dibayarkan oleh bank kepada pemegang rekening sebagai imbalan atas penggunaan uang mereka oleh bank. Data suku bunga tabungan sering menunjukkan volatilitas yang tinggi karena dipengaruhi oleh berbagai faktor ekonomi, kebijakan moneter, dan kondisi pasar. Volatilitas ini menimbulkan tantangan dalam peramalan suku bunga tabungan, karena perubahan kecil dalam data historis dapat berdampak besar pada proyeksi masa depan, sehingga diperlukan model peramalan yang mampu menangani volatilitas ini dengan efektif. Model ARIMA (Autoregressive Integrated Moving Average) dikombinasikan dengan ARCH (Autoregressive Conditional Heteroskedasticity) atau GARCH (Generalized Autoregressive Conditional Heteroskedasticity) merupakan pendekatan yang tepat untuk meramalkan data suku bunga tabungan yang memiliki volatilitas yang tinggi. ARIMA mampu menangkap pola data jangka panjang dan tren linier, sedangkan ARCH/GARCH dapat menangani heteroskedastisitas, yaitu variabilitas (atau varian) dari residual tidak konstan dan berubah-ubah seiring waktu. Penelitian ini menerapkan model ARIMA yang digunakan untuk menangkap komponen tren dan model ARCH/GARCH digunakan untuk memodelkan volatilitas sisa (residual) model ARIMA dari data suku bunga tabungan pada kelompok Bank Persero. Penelitian ini menghasilkan model yang layak digunakan untuk meramalkan nilai suku bunga tabungan pada kelompok Bank Persero. Model-model tersebut adalah model ARIMA(5,1,0)-GARCH(1,1), ARIMA([1,16],1,1) GARCH(1,1), dan ARIMA(16,1,[1,5,17])-GARCH(1,1). Kriteria pemilihan model terbaik menggunakan MAPE dengan model ARIMA(5,1,0)-GARCH(1,1) memiliki nilai MAPE sebesar 3.10%, model ARIMA([1,16],1,1)-GARCH(1,1) memiliki nilai MAPE sebesar 4.33%, dan model ARIMA(16,1,[1,5,17])-GARCH(1,1) memiliki nilai MAPE sebesar 9.44%, sehingga model terbaik untuk meramalkan nilai suku bunga tabungan pada kelompok Bank Persero yaitu model ARIMA(5,1,0)-GARCH(1,1).
==============================================================================================================================
The savings interest rate is a certain percentage of the savings balance paid by the bank to the account holder in return for the bank’s use of their money. Savings interest rate data often shows high volatility because it is influenced by various economic factors, monetary policy and market conditions. This volatility creates challenges in forecasting savings interest rates, because small changes in historical data can have a large impact on future projections, so a forecasting model is needed that is able to handle this volatility effectively. The ARIMA (Autoregressive Integrated Moving Average) model combined with ARCH(Autoregressive Conditional Heteroskedasticity) or GARCH (Generalized Autoregressive Conditional Heteroskedasticity) is the right approach for forecasting savings interest rate data that has high volatility. ARIMA is able to capture long-term data patterns and linear trends, while ARCH/GARCH can handle heteroscedasticity, namely the variability (or variance) of the residuals is not constant and changes over time. This research applies the ARIMA model which is used to capture trend components and the ARCH/GAR CH model is used to model the residual volatility of the ARIMA model from savings interest rate data in the Persero Bank group. This research produces a model that is suitable to be used to predict the value of savings interest rates in the Bank Persero group. The se models are ARIMA(5,1,0)-GARCH(1,1), ARIMA([1,16],1,1)-GARCH(1,1), and ARI MA(16,1,[ 1,5,17])-GARCH(1,1). The criteria for selecting the best model use MAPE, with MAPE results of 3.10% for the ARIMA(5,1,0)-GARCH(1,1) model, 4.33% for the ARIMA([1,16],1,1)-GARCH(1, 1), and 9.44% for the ARIMA(16,1,[1,5,17])-GARCH(1,1) model, so the best model for predicting the value of savings interest rates in the Persero Bank group is ARIMA(5,1, 0)-GARCH(1,1).
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Interest Rate, ARIMA, ARCH, GARCH, Suku Bunga |
| Subjects: | Q Science > QA Mathematics |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis |
| Depositing User: | Nida Atus Sa'adah |
| Date Deposited: | 06 Aug 2024 08:28 |
| Last Modified: | 28 Aug 2024 06:12 |
| URI: | http://repository.its.ac.id/id/eprint/113691 |
Actions (login required)
 |
View Item |