Ramadhanti, Amirah Rizky (2026) Implementasi Model Geometric Brownian Motion dan Cornish-Fisher Expansion untuk Prediksi Risiko Kerugian pada Saham Indofood Group. Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text (COVER)
22083010036-COVER.pdf Download (1MB) | Preview |
|
|
Text (BAB I)
22083010036-BAB I.pdf Download (252kB) | Preview |
|
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (BAB II)
22083010036-BAB II.pdf Restricted to Repository staff only until 19 May 2028. Download (588kB) |
|
|
Text (BAB III)
22083010036-BAB III.pdf Restricted to Repository staff only until 19 May 2028. Download (511kB) |
|
|
Text (BAB IV)
22083010036-BAB IV.pdf Restricted to Repository staff only until 19 May 2028. Download (2MB) |
|
|
Text (BAB V)
22083010036-BAB V.pdf Download (320kB) | Preview |
|
|
Text (DAFTAR PUSTAKA)
22083010036-DAFTAR PUSTAKA.pdf Download (192kB) | Preview |
|
|
Text (LAMPIRAN)
22083010036-LAMPIRAN.pdf Restricted to Repository staff only Download (363kB) |
Abstract
The Indonesian capital market faced significant macroeconomic pressure during the 2024–2025 period, marked by the weakening of the Rupiah exchange rate to Rp16,700 per USD, which suppressed the stock performance of PT Indofood Sukses Makmur Tbk (INDF) and PT Indofood CBP Sukses Makmur Tbk (ICBP). The primary issue in this phenomenon is the stochastic nature of stock price movements, which are difficult to predict with certainty and challenging to map using standard linear mathematical models. This research is essential as investors require forecasting and risk estimation methods capable of handling dynamic price fluctuations to accurately anticipate potential investment losses. This study aims to model stock prices using Geometric Brownian Motion (GBM) and measure investment risk through the Value at Risk Cornish-Fisher Expansion (VaR-CFE) approach, integrated into a Streamlit interface. The results show that the GBM model is highly accurate, with the lowest MAPE values of 1.30% for INDF (∆t=1) and 3.50% for ICBP (∆t=2). Risk measurement using VaR-CFE proved to be highly effective and valid for the daily interval (∆t=1), demonstrated by a low and consistent violation rate of 5.26% at the 95% confidence level for both issuers. However, at a longer time interval (∆t=3), the model showed high sensitivity to market shocks, with violations jumping to 50% for ICBP, reflecting the significant impact of extreme risk during the crisis period. In conclusion, the integration of GBM and VaR-CFE is capable of producing realistic price projections and accurate risk estimates for the short term, providing a solid foundation for investors in decision-making within the consumer non-cyclicals sector.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Data Science | ||||||||||||
| Depositing User: | Amirah Rizky Ramadhanti | ||||||||||||
| Date Deposited: | 20 May 2026 04:09 | ||||||||||||
| Last Modified: | 20 May 2026 04:09 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/51915 |
Actions (login required)
 |
View Item |