Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

FORECASTING INDONESIAN INFLATION: A RECURRENT NEURAL NETWORK-BASED DEEP LEARNING APPROACH

Jurnal Ilmiah Ilmu Terapan Universitas Jambi · Vol. 10 No. 5 (2026) · hlm. 2370–2380

DOI
10.22437/jiituj.v10i5.53969
ISSN
2580-2259, 2580-2240
Terbit
2026-09-18
Penerbit
LPPM Universitas Jambi
Bahasa
en
Lisensi
creativecommons.org/licenses/by/4.0

Abstrak

Forecasting models in the economic field have traditionally relied on conventional statistical methods. However, these methods often face limitations when dealing with volatile and non-stationary data, such as inflation in Indonesia. A deep learning approach based on Recurrent Neural Networks (RNN) is proposed as an alternative for forecasting Indonesian inflation. This study aims to evaluate the accuracy of the RNN method as a forecasting model for inflation in Indonesia. The study employs a quantitative time-series forecasting design using secondary monthly inflation data from January 2003 to January 2026, collected from Bank Indonesia. The analytical framework uses an RNN-based deep learning model with hyperparameter optimization, Min-Max Scaling, and a chronological 70:30 train-test split. Model performance is evaluated using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The results indicate that the optimal forecasting performance is achieved using the Tanh activation function, 10 RNN units, and a dropout rate of 0.05, with an RMSE of 0.369869 and an MAE of 0.266443 on the test data. The RNN model projects a stable inflation trend ranging from 3.38% to 3.9475%. These findings suggest that RNN can serve as a complementary approach for forecasting Indonesian inflation.

Kata kunci

Jaringan kolaborasi para penulis

9 penulis · 20 tautan kepenulisan bersama · 10 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Jenderal Soedirman University
  • Sebelas Maret University
  • Universitas Islam Negeri Profesor Kiai Haji Saifuddin Zuhri Purwokerto
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Fajar HardoyonoUniversitas Islam Negeri Profesor Kiai Haji Saifuddin Zuhri Purwokerto2
Tri MulyaningsihSebelas Maret University1
Bhimo Rizky SamudroSebelas Maret University1
Yunastiti PurwaningsihSebelas Maret University1
Ratna Setyawati GunawanJenderal Soedirman University1
Dicky Satria RamadhanJenderal Soedirman University1
Anzar Alfat FirdausJenderal Soedirman University1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://online-journal.unja.ac.id/index.php/JIITUJ/oai, pertama di-harvest 5 Nov 2026, terakhir terlihat 15 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">FORECASTING INDONESIAN INFLATION: A RECURRENT NEURAL NETWORK-BASED DEEP LEARNING APPROACH</dc:title>
	<dc:creator xml:lang="en">Adyatma, Wimala Eka</dc:creator>
	<dc:creator xml:lang="en">Windhani, Kikin</dc:creator>
	<dc:subject xml:lang="en">Deep Learning</dc:subject>
	<dc:subject xml:lang="en">Forecasting</dc:subject>
	<dc:subject xml:lang="en">Inflation</dc:subject>
	<dc:subject xml:lang="en">Recurrent Neural Network</dc:subject>
	<dc:description xml:lang="en">Forecasting models in the economic field have traditionally relied on conventional statistical methods. However, these methods often face limitations when dealing with volatile and non-stationary data, such as inflation in Indonesia. A deep learning approach based on Recurrent Neural Networks (RNN) is proposed as an alternative for forecasting Indonesian inflation. This study aims to evaluate the accuracy of the RNN method as a forecasting model for inflation in Indonesia. The study employs a quantitative time-series forecasting design using secondary monthly inflation data from January 2003 to January 2026, collected from Bank Indonesia. The analytical framework uses an RNN-based deep learning model with hyperparameter optimization, Min-Max Scaling, and a chronological 70:30 train-test split. Model performance is evaluated using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The results indicate that the optimal forecasting performance is achieved using the Tanh activation function, 10 RNN units, and a dropout rate of 0.05, with an RMSE of 0.369869 and an MAE of 0.266443 on the test data. The RNN model projects a stable inflation trend ranging from 3.38% to 3.9475%. These findings suggest that RNN can serve as a complementary approach for forecasting Indonesian inflation.</dc:description>
	<dc:publisher xml:lang="en">LPPM Universitas Jambi</dc:publisher>
	<dc:date>2026-09-18</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://online-journal.unja.ac.id/JIITUJ/article/view/53969</dc:identifier>
	<dc:identifier>10.22437/jiituj.v10i5.53969</dc:identifier>
	<dc:source xml:lang="en">Jurnal Ilmiah Ilmu Terapan Universitas Jambi; Vol. 10 No. 5 (2026): Volume 10, Nomor 5, October 2026; 2370-2380</dc:source>
	<dc:source>2580-2259</dc:source>
	<dc:source>2580-2240</dc:source>
	<dc:source>10.22437/jiituj.v10i5</dc:source>
	<dc:language>en</dc:language>
	<dc:relation>https://online-journal.unja.ac.id/JIITUJ/article/view/53969/25685</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2026 Wimala Eka Adyatma, Kikin Windhani</dc:rights>
	<dc:rights xml:lang="en">https://creativecommons.org/licenses/by/4.0</dc:rights>
</oai_dc:dc>