Sitorus, Jocelyne Sharon Geraldine (2026) Peramalan Kurs, Indeks Harga Saham Gabungan, Dan Harga Minyak Dunia Menggunakan Metode Vector Autoregressive Integrated Moving Average Dan Kalman Filter. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5002221087_Undergraduate Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5002221087_Undergraduate Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy |
Abstract
Nilai tukar Rupiah terhadap USD, Indeks Harga Saham Gabungan (IHSG), dan harga minyak dunia merupakan indikator ekonomi yang saling berkaitan dan bersifat fluktuatif, sehingga perubahan pada salah satu variabel dapat memengaruhi variabel lainnya. Penelitian ini bertujuan untuk memperoleh model peramalan terbaik bagi ketiga variabel tersebut dengan pendekatan multivariat yang mampu menangkap hubungan dinamis secara simultan. Metode univariat dianggap kurang memadai karena mengabaikan keterkaitan antarvariabel, sehingga digunakan Vector Autoregressive Integrated Moving Average (VARIMA) yang memodelkan seluruh variabel sebagai endogen dalam satu sistem. VARIMA memiliki keterbatasan kurang responsif terhadap perubahan data terkini, untuk mengatasi hal tersebut model VARIMA direpresentasikan ke dalam bentuk state-space dan diproses menggunakan algoritma Kalman Filter yang bekerja secara rekursif untuk memperbarui estimasi state setiap kali data observasi baru masuk. Berdasarkan hasil analisis, diperoleh model VARIMA(1,1,0) sebagai model terbaik berdasarkan AIC terkecil dan telah memenuhi uji diagnostik white noise. Hasil peramalan VARIMA(1,1,0) nilai MAPE sebesar 2,0991% untuk Kurs USD/IDR, 6, 1768% untuk IHSG, dan 31, 9947% untuk harga minyak dunia. Setelah diterapkan Kalman Filter, MAPE menjadi 1,867% untuk Kurs USD/IDR, 4, 6946% untuk IHSG, dan 9, 1376% untuk harga minyak dunia. Hal ini menunjukkan bahwa metode VARIMA(1,1,0)-Kalman Filter mampu menghasilkan peramalan yang lebih akurat.
======================================================================================================================================
The USD/IDR exchange rate, the Indonesia Composite Stock Price Index (IHSG), and world oil prices are interrelated and fluctuating economic indicators,such that changes in one variable can affect the others. This study aims to obtain the best forecasting model for these three variables using multivariate approach capable of capturing dynamic relationships simultaneously. Univariate methods are considered inadequate, leading to the use of the Vector Autoregressive Integrated Moving Average (VARIMA) model, which treats all variables as endogenous within a single system. VARIMA has a limitation in that it is less responsive to recent changes in data, to addres this issue, the VARIMA model is represented in a state-space form and processed using the Kalman Filter algorthm, which works recursively to update state estimates, whenever new observational data are variable. Based on analysis, the VARIMA(1,1,0) model was selected as the best model based on the smallest Akaike Informastion Criterion (AIC) and has passed the white noise diagnostic test. The forecasting results using VARIMA(1,1,0) yield MAPE values of 2,0991% for the exchange rate, 6,1768% for the IHSG, and 31,9947% for world oil prices. After, applying the Kalman Filter , the MAPE values improve to 1.867% for the USD/IDR exchange rate, 4, 6946% for IHSG, and 9, 1376% for world oil prices. This indicates that the VARIMA(1,1,0)-Kalman Filter method is capable of producing more accurate forecats.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | ARIMA, Kalman Filter, Kurs, IHSG, Harga Minyak dunia, Multivariat VARIMA, Kalman Filter, Exchange Rate, IHSG, World Oil Prices, Multivariate Forecasting |
| Subjects: | Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA402.3 Kalman filtering. |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis |
| Depositing User: | Jocelyne Sharon Geraldine Sitorus |
| Date Deposited: | 30 Jul 2026 04:49 |
| Last Modified: | 30 Jul 2026 04:49 |
| URI: | http://repository.its.ac.id/id/eprint/139891 |
Actions (login required)
 |
View Item |