Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Prismatika: Jurnal Pendidikan dan Riset Matematika
Juniasti Gulo
Unknown Affiliation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
PREDIKSI HARGA TANDAN BUAH SEGAR KELAPA SAWIT MENGGUNAKAN MODEL GATED RECURRENT UNIT DI PROVINSI JAMBI Juniasti Gulo; Yurinanda, Sherli; Sormin, Corry
Prismatika: Jurnal Pendidikan dan Riset Matematika Vol. 8 No. 1 (2025): Prismatika: Jurnal Pendidikan dan Riset Matematika
Publisher : Universitas Insan Budi Utomo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33503/prismatika.v8i1.2138

Abstract

Oil palm is a leading commodity that plays a strategic role in Indonesia’s agricultural sector. Jambi Province is one of the main producers of fresh fruit bunches (FFB) is the main harvest product of oil palm. Although production levels are high and global demand continues to increase, FFB prices tend to fluctuate, creating income uncertainty for both farmers and industry players. These fluctuations are influenced by various factors and require a modeling approach capable of capturing historical patterns in time series data that are nonlinear and volatile. This study aims to apply the Gated Recurrent Unit (GRU) model to predict oil palm FFB prices in Jambi Province. GRU is selected because it is effective in processing sequential data and retaining long-term information through its update gate and reset gate mechanisms. The data used consist of daily FFB prices over the past three years. The research process includes preprocessing, normalization using the min–max scaler, data splitting (80% training and 20% testing), model training with various hyperparameter combinations, and evaluation using Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). The results show that the GRU model successfully captures the historical patterns of FFB prices. The best configuration was obtained with a learning rate of 0.01, hidden size of 128, batch size of 16, window size of 5, and 100 epochs. The model achieved an MSE of 0.0418 on the training data and a MAPE of 12.82% for the 50-day forecast. These values indicate a good level of accuracy, suggesting that the GRU model is suitable as a data-driven decision support tool to enhance price stability and assist plantation business planning in Jambi Province.
Co-Authors Sormin, Corry Yurinanda, Sherli