Abrory, Moh. Wahyu (2026) KOMPARASI MODEL LSTM DAN GRU UNTUK PREDIKSI HARGA EMAS BERDASARKAN INFLASI, NILAI TUKAR, DAN SUKU BUNGA. Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text
22082010075-cover.pdf Download (548kB) | Preview |
|
|
Text (Bab 1)
22082010075-bab1.pdf Download (476kB) | Preview |
|
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Bab 2)
22082010075-bab2.pdf Restricted to Repository staff only until 25 May 2029. Download (601kB) |
|
|
Text (Bab 3)
22082010075-bab3.pdf Restricted to Repository staff only until 25 May 2029. Download (540kB) |
|
|
Text (Bab 4)
22082010075-bab4.pdf Restricted to Repository staff only until 25 May 2029. Download (953kB) |
|
|
Text (Bab 5)
22082010075-bab5.pdf Download (243kB) | Preview |
|
|
Text (Daftar Pustaka)
22082010075-daftarpustaka.pdf Download (184kB) | Preview |
|
|
Text (Lampiran)
22082010075-lampiran.pdf Restricted to Repository staff only until 25 May 2029. Download (913kB) |
Abstract
Gold is a strategic asset widely used as a hedging instrument in Indonesia, with its price being highly influenced by domestic macroeconomic factors including inflation, Bank Indonesia's benchmark interest rate, and the USD/IDR exchange rate. Classical statistical models such as ARIMA have limitations in capturing nonlinear patterns and long-term dependencies in financial time series data. This study aimed to compare the performance of two deep learning algorithms, Long ShortTerm Memory (LSTM) and Gated Recurrent Unit (GRU), in predicting the daily price of ANTAM LM gold based on the aforementioned macroeconomic variables. Data covering the period from January 2015 to September 2025 were obtained from PT Antam, Bank Indonesia, and Investing.com. The research process included data collection, preprocessing, exploratory data analysis, dataset splitting, model training, and evaluation using RMSE and MAPE metrics. The evaluation results demonstrated that GRU achieved the best performance under the 90:10 split scheme with an RMSE of IDR 35,417.91 and a MAPE of 1.47%, outperforming the best LSTM model which recorded an RMSE of IDR 96,808.4 and a MAPE of 4.58%. The best-performing model, GRU, was deployed into a Flask-based web application that enabled users to interactively select prediction horizons, serving as a tool for investment decision-making. This research contributed to the development of a practical deep learning-based commodity price prediction system applicable to the Indonesian market context.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > QA Mathematics > QA76 Computer software Q Science > QA Mathematics > QA76.6 Computer Programming Q Science > QA Mathematics > QA76.87 Neural computers |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Information Systems | ||||||||||||
| Depositing User: | Moh. Wahyu Abrory | ||||||||||||
| Date Deposited: | 26 May 2026 01:58 | ||||||||||||
| Last Modified: | 26 May 2026 03:11 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/52530 |
Actions (login required)
 |
View Item |