Skripsi

PERAMALAN HARGA MINYAK MENTAH DI PASAR GLOBAL BERBASIS MODEL LONG SHORT TERM MEMORY

---

Crude oil price forecasting plays an important role in supporting economic decision-making, as oil price fluctuations directly affect global stability. This study employs a Long Short-Term Memory (LSTM) model to predict West Texas Intermediate (WTI) crude oil prices, with a focus on the influence of the hyperparameters lookback and the number of epochs on model performance. The findings indicate that parameter selection greatly impacts the effectiveness of the model. A lookback window that is too short leads to the loss of essential temporal information, while an excessively long lookback increases the risk of overfitting. Similarly, a very high number of epochs does not always result in improved accuracy and may even reduce the model’s generalization capability. The optimal configuration was found with a lookback of 35 and 110 epochs, achieving an RMSE of 6.6310 and a MAPE of 9.52%. These results emphasize that achieving balance in hyperparameter selection is crucial to obtain accurate predictive outcomes while maintaining the model’s robustness against data variability.

---

Availability

Detail Information

Series Title

-

Call Number

T1977882026

Publisher

Indralaya : Prodi Magister Ilmu Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xvi, 146 hlm.; ilus.; tab, 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.320 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Magister Ilmu Komputer
Kecerdasan Buatan — Penerapan

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment