THE COMPARISON OF LONG SHORT-TERM MEMORY AND BIDIRECTIONAL LONG SHORT-TERM MEMORY FOR FORECASTING COAL PRICE

Coal remains vital for global energy despite recent demand fluctuations due to the COVID-19 pandemic and geopolitical tensions. The International Energy Agency (IEA) projected a decline in global coal demand starting in early 2024, driven by increasing renewable energy adoption. As one of the top co...

Full description

Saved in:
Bibliographic Details
Main Authors: Indra Rivaldi Siregar, Adhiyatma Nugraha, Khairil Anwar Notodiputro, Yenni Angraini, Laily Nissa Atul Mualifah
Format: Article
Language:English
Published: Universitas Pattimura 2025-01-01
Series:Barekeng
Subjects:
Online Access:https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/13416
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849389600678608896
author Indra Rivaldi Siregar
Adhiyatma Nugraha
Khairil Anwar Notodiputro
Yenni Angraini
Laily Nissa Atul Mualifah
author_facet Indra Rivaldi Siregar
Adhiyatma Nugraha
Khairil Anwar Notodiputro
Yenni Angraini
Laily Nissa Atul Mualifah
author_sort Indra Rivaldi Siregar
collection DOAJ
description Coal remains vital for global energy despite recent demand fluctuations due to the COVID-19 pandemic and geopolitical tensions. The International Energy Agency (IEA) projected a decline in global coal demand starting in early 2024, driven by increasing renewable energy adoption. As one of the top coal exporters, Indonesia must adjust to these changes. This study aims to forecast future coal prices using historical data from Indonesia's Ministry of Energy and Mineral Resources (KESDM), applying and comparing Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) models. While BiLSTM has shown advantages in other contexts and studies, its effectiveness for coal price forecasting remains underexplored. To ensure robust predictions, we employ walk-forward validation, which divides the data into six segments and evaluates 90 hyperparameter combinations across all segments. The BiLSTM model consistently outperforms the LSTM model, achieving lower average RMSE and MAPE values. Specifically, BiLSTM records an average MAPE of 7.847 and RMSE of 10.485, compared to LSTM's 10.442 and 11.993, respectively. The Diebold-Mariano (DM) test using squared error and absolute error loss functions further corroborates these findings, with most segments showing significant improvements in favor of BiLSTM, indicated by negative DM-test statistics and p-values below 0.01 or 0.10. This superior performance continues into the testing data, where BiLSTM maintains lower error metrics and a significant result of the DM test, underscoring its reliability for forecasting. In the final stage, the forecasts from both models indicate a nearly linear downward trend in coal prices over the next 18 months, aligning with the International Energy Agency's 2023 projection of a structural decline in coal demand driven by the sustained growth of clean energy technologies.
format Article
id doaj-art-bb503fffe8494984b00bba8bd306a535
institution Kabale University
issn 1978-7227
2615-3017
language English
publishDate 2025-01-01
publisher Universitas Pattimura
record_format Article
series Barekeng
spelling doaj-art-bb503fffe8494984b00bba8bd306a5352025-08-20T03:41:56ZengUniversitas PattimuraBarekeng1978-72272615-30172025-01-0119124525810.30598/barekengvol19iss1pp245-25813416THE COMPARISON OF LONG SHORT-TERM MEMORY AND BIDIRECTIONAL LONG SHORT-TERM MEMORY FOR FORECASTING COAL PRICEIndra Rivaldi Siregar0Adhiyatma Nugraha1Khairil Anwar Notodiputro2Yenni Angraini3Laily Nissa Atul Mualifah4Department of Statistics, Faculty of Mathematics and Natural Sciences, IPB University, IndonesiaDepartment of Statistics, Faculty of Mathematics and Natural Sciences, IPB University, IndonesiaDepartment of Statistics, Faculty of Mathematics and Natural Sciences, IPB University, IndonesiaDepartment of Statistics, Faculty of Mathematics and Natural Sciences, IPB University, IndonesiaDepartment of Statistics, Faculty of Mathematics and Natural Sciences, IPB University, IndonesiaCoal remains vital for global energy despite recent demand fluctuations due to the COVID-19 pandemic and geopolitical tensions. The International Energy Agency (IEA) projected a decline in global coal demand starting in early 2024, driven by increasing renewable energy adoption. As one of the top coal exporters, Indonesia must adjust to these changes. This study aims to forecast future coal prices using historical data from Indonesia's Ministry of Energy and Mineral Resources (KESDM), applying and comparing Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) models. While BiLSTM has shown advantages in other contexts and studies, its effectiveness for coal price forecasting remains underexplored. To ensure robust predictions, we employ walk-forward validation, which divides the data into six segments and evaluates 90 hyperparameter combinations across all segments. The BiLSTM model consistently outperforms the LSTM model, achieving lower average RMSE and MAPE values. Specifically, BiLSTM records an average MAPE of 7.847 and RMSE of 10.485, compared to LSTM's 10.442 and 11.993, respectively. The Diebold-Mariano (DM) test using squared error and absolute error loss functions further corroborates these findings, with most segments showing significant improvements in favor of BiLSTM, indicated by negative DM-test statistics and p-values below 0.01 or 0.10. This superior performance continues into the testing data, where BiLSTM maintains lower error metrics and a significant result of the DM test, underscoring its reliability for forecasting. In the final stage, the forecasts from both models indicate a nearly linear downward trend in coal prices over the next 18 months, aligning with the International Energy Agency's 2023 projection of a structural decline in coal demand driven by the sustained growth of clean energy technologies.https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/13416bilstmcoal pricelstmtime serieswalk forward validation
spellingShingle Indra Rivaldi Siregar
Adhiyatma Nugraha
Khairil Anwar Notodiputro
Yenni Angraini
Laily Nissa Atul Mualifah
THE COMPARISON OF LONG SHORT-TERM MEMORY AND BIDIRECTIONAL LONG SHORT-TERM MEMORY FOR FORECASTING COAL PRICE
Barekeng
bilstm
coal price
lstm
time series
walk forward validation
title THE COMPARISON OF LONG SHORT-TERM MEMORY AND BIDIRECTIONAL LONG SHORT-TERM MEMORY FOR FORECASTING COAL PRICE
title_full THE COMPARISON OF LONG SHORT-TERM MEMORY AND BIDIRECTIONAL LONG SHORT-TERM MEMORY FOR FORECASTING COAL PRICE
title_fullStr THE COMPARISON OF LONG SHORT-TERM MEMORY AND BIDIRECTIONAL LONG SHORT-TERM MEMORY FOR FORECASTING COAL PRICE
title_full_unstemmed THE COMPARISON OF LONG SHORT-TERM MEMORY AND BIDIRECTIONAL LONG SHORT-TERM MEMORY FOR FORECASTING COAL PRICE
title_short THE COMPARISON OF LONG SHORT-TERM MEMORY AND BIDIRECTIONAL LONG SHORT-TERM MEMORY FOR FORECASTING COAL PRICE
title_sort comparison of long short term memory and bidirectional long short term memory for forecasting coal price
topic bilstm
coal price
lstm
time series
walk forward validation
url https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/13416
work_keys_str_mv AT indrarivaldisiregar thecomparisonoflongshorttermmemoryandbidirectionallongshorttermmemoryforforecastingcoalprice
AT adhiyatmanugraha thecomparisonoflongshorttermmemoryandbidirectionallongshorttermmemoryforforecastingcoalprice
AT khairilanwarnotodiputro thecomparisonoflongshorttermmemoryandbidirectionallongshorttermmemoryforforecastingcoalprice
AT yenniangraini thecomparisonoflongshorttermmemoryandbidirectionallongshorttermmemoryforforecastingcoalprice
AT lailynissaatulmualifah thecomparisonoflongshorttermmemoryandbidirectionallongshorttermmemoryforforecastingcoalprice
AT indrarivaldisiregar comparisonoflongshorttermmemoryandbidirectionallongshorttermmemoryforforecastingcoalprice
AT adhiyatmanugraha comparisonoflongshorttermmemoryandbidirectionallongshorttermmemoryforforecastingcoalprice
AT khairilanwarnotodiputro comparisonoflongshorttermmemoryandbidirectionallongshorttermmemoryforforecastingcoalprice
AT yenniangraini comparisonoflongshorttermmemoryandbidirectionallongshorttermmemoryforforecastingcoalprice
AT lailynissaatulmualifah comparisonoflongshorttermmemoryandbidirectionallongshorttermmemoryforforecastingcoalprice