Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Integra: Journal of Integrated Mathematics and Computer Science

A Hybrid ARIMA–GRU Model for Forecasting Palm Oil Prices at PT Sawit Sumbermas Sarana in Central Kalimantan Kurniasari, Dian; Shella, Tiara Pramay; Usman, Mustofa; Warsono
Integra: Journal of Integrated Mathematics and Computer Science Vol. 2 No. 1 (2025): March
Publisher : Magister Program of Mathematics, Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/integrajimcs.20252112

Abstract

The palm oil industry plays a strategic role in Indonesia's economic landscape. As one of the world’s largest producers, Indonesia holds substantial potential in marketing both crude palm oil (CPO) and palm kernel oil on domestic and international fronts. Palm oil prices consistently correlate with CPO prices, given that the pricing of palm oil is benchmarked against CPO, resulting in market fluctuations. Forecasting future palm oil prices becomes an essential measure in response to this volatility. The ARIMA (AutoRegressive Integrated Moving Average) model has been widely recognized as a reliable method for time series forecasting. Despite its strengths, ARIMA faces challenges in identifying the non-linear components that are often present in real-world data. The Gated Recurrent Unit (GRU) model, which incorporates an update gate and a reset gate, offers an alternative that effectively captures complex non-linear patterns. A hybrid model integrating ARIMA and GRU has therefore been developed with the aim of improving predictive accuracy. This hybrid approach includes two stages: the ARIMA model for initial predictions and a GRU model that processes the residuals from the ARIMA output. In this study, the ARIMA-GRU hybrid model demonstrated strong performance, yielding a Mean Squared Error (MSE) of 868.4690, a Root Mean Squared Error (RMSE) of 29.4698, a Mean Absolute Percentage Error (MAPE) of 0.0117, and an overall accuracy of 99.9824%.
Integrating VAR and CNN Models for Accurate Forecasting of Money Supply in Indonesia Warsono; Sulandra, Ardelia Maharani; Kurniasari, Dian; Usman, Mustofa; Susetyo, Budi
Integra: Journal of Integrated Mathematics and Computer Science Vol. 2 No. 2 (2025): July
Publisher : Magister Program of Mathematics, Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/integrajimcs.20252230

Abstract

Economic forecasting serves as a fundamental element in supporting decision-making processes across multiple sectors. One of the main areas of interest in this field is the estimation of the money supply within an economy. The Vector Autoregressive (VAR) model is a commonly applied method for forecasting; however, it often encounters limitations when processing data with nonlinear patterns. Convolutional Neural Networks (CNNs) offer an alternative approach, particularly effective in identifying nonlinear structures that are not adequately captured by VAR models. A hybrid VAR-CNN model is therefore proposed, combining the respective strengths of both techniques to improve the accuracy of predictions. This research applies to the hybrid VAR-CNN model to forecast economic variables for the period from July 2022 to June 2023. The model consists of two main components: the first utilizes forecasted values generated by the VAR model, while the second processes the residuals from the VAR output using a CNN. With 80% of the data allocated for training and 20% for testing, the hybrid VAR-CNN model demonstrates improved performance over alternative forecasting methods. Evaluation based on Mean Absolute Percentage Error (MAPE), supremum (D) values, and p-values confirms the effectiveness of this hybrid approach.