Adam, Cindi (2026) Prediksi Harga Saham Dan Analisis Risiko Menggunakan Model ARIMAX Additive Outlier: Studi Kasus PT Garudafood Putra Putri Jaya Tbk. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
Cover.pdf Download (969kB) |
|
Text (Bab 1)
Bab 1.pdf Download (273kB) |
|
Text (Bab 2)
Bab 2.pdf Restricted to Repository staff only until 22 September 2028. Download (713kB) |
|
Text (Bab 3)
Bab 3.pdf Restricted to Repository staff only until 22 September 2028. Download (665kB) |
|
Text (Bab 4)
Bab 4.pdf Restricted to Repository staff only until 22 September 2028. Download (1MB) |
|
Text (Bab 5)
Bab 5.pdf Download (244kB) |
|
Text (Daftar Puskata)
Daftar Pustaka.pdf Download (232kB) |
|
Text (Lampiran)
Lampiran.pdf Restricted to Repository staff only Download (804kB) |
Abstract
The stock price of PT Garudafood Putra Putri Jaya Tbk (GOOD.JK) exhibits dynamic movements, with relatively large changes in returns during several periods. Such conditions may increase uncertainty in price movements and potential investment losses, requiring a method that can simultaneously forecast stock prices and measure stock risk. This study employs the Autoregressive Integrated Moving Average Exogenous with Additive Outlier (ARIMAX-AO) model to forecast stock returns and prices by considering exogenous variables and Additive Outlier events. Stock risk is subsequently measured using Value at Risk (VaR) with the Filtered Historical Simulation (FHS) approach. The data consist of daily GOOD.JK observations from January 2019 to August 2026, with stock returns as the dependent variable and IHSG returns and USD/IDR exchange rate returns as exogenous variables. The results show that the ARIMAX-AO(0,0,2) model with ten Additive Outlier dummy variables performs better than the ARIMAX(0,0,2) model, with an AIC of -8453.05, BIC of -8368.30, RMSE of 21.55, MAE of 18.72, and MAPE of 5.38%. The forecasting results indicate that the stock price is expected to increase slightly at the beginning of the forecast period and then gradually decline from IDR 318.36 on September 1, 2026, to IDR 317.20 on September 18, 2026. The ARCH-LM test indicates the presence of an ARCH effect in the residuals; therefore, volatility modeling is performed using GARCH(1,3). The VaR results show that the 95% VaR ranges from -1.4726% to -2.2626%, while the 99% VaR ranges from -2.6092% to -3.7374%. The Kupiec test results indicate that both the 95% and 99% VaR meet the validity criteria and can therefore be used to measure the risk of GOOD.JK stock.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | H Social Sciences > HA Statistics | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Data Science | ||||||||||||
| Depositing User: | Cindi Adam | ||||||||||||
| Date Deposited: | 22 Sep 2026 08:09 | ||||||||||||
| Last Modified: | 22 Sep 2026 08:09 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/60260 |
Actions (login required)
 |
View Item |