A Hybrid Convolutional Neural Network and Bidirectional LSTM Architecture for Multi-Sector Export Forecasting: A Macroeconomic Time Series Analysis of Indonesia

Desi Anggreani; Nurmisba Nurmisba; Aedah Abd Rahman

doi:10.56705/ijodas.v6i3.330

Authors

Desi Anggreani Universitas Muhammadiyah Makassar
Nurmisba Nurmisba Universitas Muhammadiyah Makassar
Aedah Abd Rahman Asia E University

DOI:

https://doi.org/10.56705/ijodas.v6i3.330

Keywords:

Bidirectional LSTM, Convolutional Neural Network, Hybrid Architecture, Export Forecasting, Time Series Analysis

Abstract

Accurately predicting export values is key for a country in formulating its economic plans. Unfortunately, export data often exhibits complex time series patterns that are difficult to predict, characterized by non-linearity, high volatility, and complex temporal dependencies. This study offers a solution by testing a combined deep learning model, specifically a fusion of Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM), to address the challenges of export time series forecasting. This study uses this approach to forecast Indonesia's monthly export time series data from 2016 to 2023, covering various sectors ranging from oil and gas, non-oil and gas, agriculture, industry, mining, and others. The core idea is to leverage the CNN's ability to identify hidden features within time series patterns, while the BiLSTM is tasked with understanding the temporal flow of data from both directions to capture the inherent long-term temporal dependencies within economic time series data. As a result, this combined model proved to be far superior to the standard BiLSTM model in handling the complexity of export time series. In the Non-Oil and Gas sector, the proposed model achieved a high level of accuracy with an MSE value of 3,330,239.74, an RMSE of 1,824.89, and an average prediction error (MAPE) of only 8.17%, representing a significant improvement of 69% over the baseline BiLSTM model. Similar success was also found in all other sectors, proving that this hybrid approach is highly promising for complex economic time series analysis

Downloads

Download data is not yet available.

Author Biographies

Desi Anggreani, Universitas Muhammadiyah Makassar

Department of Informatics
Nurmisba Nurmisba, Universitas Muhammadiyah Makassar

Department of Informatics
Aedah Abd Rahman, Asia E University

School Science and Technology

References

[1] Veronica, H. Silaban, S. P. Nasution, and E. Indra, "Analysis Indonesia’s Export Value Forecasting To G20 Countries Using Long Short-Term Memory Neural Network Method," Sinkron : Jurnal Dan Penelitian Teknik Informatika, Vol. 7, No. 3, Jul. 2023. doi: 10.33395/Sinkron.V7i3.12794.
[2] Badan Pusat Statistik, "Ekspor Desember 2023 Mencapai Us22,41miliar, Naik 1,89 Persen Dibanding November 2023 Dan Impor Desember 2023 Senilai Us 19,11 Miliar, Turun 2,45 Persen Dibanding November 2023," Badan Pusat Statistik, Jan. 15, 2024. [Online]. Available: Https://Www.Bps.Go.Id/Id/Pressrelease/2024/01/15/2298/Exports-In-December-2023-Reached-Us-22-41-Billion---Imports-In-December-2023-Reached-Us-19-11-Billion.Html. [Accessed: Jul. 28, 2025].
[3] C. E. D. S. Simanungkalit, A. K. Agustin, H. A. Zanjabila, M. Iqbal, and S. Nabila, "Transformasi Kebijakan Nilai Tukar Dalam Dinamika Devisa : Analisis Peran Strategi, Tantangan Kompleks, Dan Proyeksi Adaptif Untuk Mempertahankan Stabilitas Dan Meningkatkan Prospek Devisa Nasional," JEMBA, vol. 1, no. 2, pp. 503–512, Jun. 2024. doi: 10.61722/jemba.v1i2.232.
[4] E. Dave, A. Leonardo, M. Jeanice, and N. Hanafiah, "Forecasting Indonesia Exports using a Hybrid Model ARIMA-LSTM," Procedia Computer Science, vol. 179, pp. 480-487, 2021 . doi: 10.1016/j.procs.2021.01.031. Sumber
[5] A. S. Ahmar and E. B. del Val, "Time Series Innovation: Leveraging BetaSutte Models to Enhance Indonesia's Export Price Forecasting," Journal of Applied Science Engineering Technology and Education, vol. 7, no. 1, pp. 29-40, Apr. 2025. doi: 10.35877/454RI.asci3831.
[6] L. Setiawan, D. Susanti, and R. Riaman, "Analisis Perbandingan Hasil Peramalan Harga Saham Menggunakan Model Autoregresive Integrated Moving Average dan Long Short Term Memory," Jurnal Matematika Integratif, vol. 19, no. 2, pp. 223–234, Dec. 2023. doi: 10.24198/jmi.v19.n2.42164.223-234.
[7] M. F. Ramadhan, D. Lestari, and U. Khaira, “Prediksi Harga Bitcoin Menggunakan Metode Long Short Term Memory”, Publikasi Elektronik Pengembangan Aplikasi Digital Untuk Negeri, vol. 5, no. 2, pp. 104–112, Aug. 2024. doi: 10.23960/pepadun.v5i2.193.
[8] R. N. Fitrianingsih and I. Kharisudin, "Time Series Modeling of Stock Price Using CNN-BiLSTM with Attention Mechanism," Unnes Journal of Mathematics, vol. 13, no. 1, pp. 11–20, Jun. 2025. doi: 10.15294/ujm.v13i1.13451.
[9] D. I. Puteri, "Implementasi Long Short Term Memory (LSTM) dan Bidirectional Long Short Term Memory (BiLSTM) Dalam Prediksi Harga Saham Syariah," EULER: Jurnal Ilmiah Matematika, Sains dan Teknologi, vol. 11, no. 1, pp. 35–43, Jun. 2023. doi: 10.34312/euler.v11i1.19791.
[10] R. Muhammad and I. Nurhaida, "Penerapan LSTM Dalam Deep Learning Untuk Prediksi Harga Kopi Jangka Pendek dan Jangka Panjang," JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 10, no. 1, pp. 554–564, Mar. 2025. doi: 10.29100/jipi.v10i1.5904.
[11] S. M. Hasanat et al., "Enhancing Load Forecasting Accuracy in Smart Grids: A Novel Parallel Multichannel Network Approach Using 1D CNN and Bi-LSTM Models," International Journal of Energy Research, vol. 2024, no. 1, Art. no. 2403847, Jul. 2024, doi: 10.1155/2024/2403847.
[12] D. Sawitri, "Peran Deep Learning dan Big Data Dalam Mendeteksi Masalah Keuangan," Djtechno: Jurnal Teknologi Informasi, vol. 6, no. 1, Apr. 2025. doi: 10.46576/djtechno.
[13] Nurfalinda, M. A. Fiani, and M. R. Rathomi, "Maximum Temperature Prediction in Tanjungpinang City Using the CNN-LSTM Model," Komputa : Jurnal Ilmiah Komputer dan Informatika, vol. 14, no. 1, May 2025. doi: 10.34010/komputa.v14i1.15377.
[14] P. N. Yulisa, M. Al Haris, and P. R. Arum, "Peramalan Nilai Ekspor Migas di Indonesia dengan Model Long Short Term Memory (LSTM) dan Gated Recurrent Unit (GRU)," Jurnal Ilmiah Teori dan Aplikasi Statistika, vol. 16, no. 1, 2023. doi: 10.36456/jstat.vol16.no1.a6121.
[15] R. Andika and K. Kusrini, "Optimasi Hyperparameter Model Lstm dan Variannya Untuk Pembelian Bahan Baku Karet Alam," JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 10, no. 3, 2025. doi: 10.29100/jipi.v10i3.7567.
[16] I. Winarni and N. Pratiwi, "Prediksi Harga Saham Menggunakan Metode Long Short Term Memory Studi Kasus: Saham Intel Corporation," DECODE: Jurnal Pendidikan Teknologi Informasi, vol. 5, no. 2, pp. 380-390, Jul. 2025. doi: 10.51454/decode.v5i2.1192.
[1] A. Yusuf, "Prediksi Indeks Harga Saham Gabungan (IHSG) Menggunakan Long Short-Term Memory," Jurnal Epsilon, vol. 15, no. 2, pp. 124–132, Des. 2021. [Online]. Available: https://repo-dosen.ulm.ac.id/handle/123456789/25605
[18] M. I. Iskandar, T. A. Mudzakir, Y. Cahyana, and A. R. Pratama, "Prediksi Pola Pergerakan Saham Adro.Jk Melalui Model LSTM Berbasis Data Historis," Bulletin of Computer Science Research, vol. 5, no. 4, Jun. 2025. doi: 10.47065/bulletincsr.v5i4.554.
[19] A. H. Pradhana, E. Daniati, and M. N. Muzaki, "Penerapan Bi-LSTM Untuk Named Entity Recognition Pada Teks Bahasa Indonesia," The Indonesian Journal of Computer Science Research, vol. 4, no. 2, pp. 96–106, 2025. doi: 10.59095/ijcsr.v4i2.208.
[20] B. A. Septian and U. T. Kartini, "Pemodelan Peramalan Beban Jangka Pendek untuk Subsistem Krian Gresik Menggunakan Deep Learning LSTM-NN," Jurnal Teknik Elektro, vol. 12, no. 2, pp. 1–5, May 2023. doi: 10.26740/jte.v12n2.p1-5.
[21] Sukatmo, H. A. Nugroho, B. H. Rusanto, and S. Soekirno, "Performance Comparison of 1D-CNN and LSTM Deep Learning Models for Time Series-Based Electric Power Prediction," ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, vol. 13, no. 1, pp. 43-56, Jan. 2025. doi: 10.26760/elkomika.v13i1.43.
[22] H. D. Diash, V. Nathania, M. Idhom, and Trimono, "Application of CNN-BiLSTM Algorithm for Ethereum Price Prediction," Journal of Applied Informatics and Computing, vol. 9, no. 4, Aug. 2025. doi: 10.30871/jaic.v9i4.9757.
[23] A. M. Almohammedi, A. Zerguine, M. Deriche and S. M. Sait, "Artificial Bee Colony DLMS Beyond Mean Square Error Boundary in Ad-hoc WSN," Computational Intelligence and Communication Networks (CICN), 2022, pp. 572-576, doi: 10.1109/CICN56167.2022.10008253.
[24] K. Rajesh and M. S. Saravanan, "Prediction of Customer Spending Score for the Shopping Mall using Gaussian Mixture Model comparing with Linear Spline Regression Algorithm to reduce Root Mean Square Error," Intelligent Computing and Control Systems (ICICCS), 2022, pp. 335-341, doi: 10.1109/ICICCS53718.2022.9788162.
[25] S. A. R. Ludeña Román, S. Zelada Collazos, and J. A. Corzo Chavez, "Model for Reducing Mean Absolute Percentage Error through Smoothing and Time Series Forecasting In a Tourism SME: A Case Study," Journal of Machine Intelligence and Data Science (JMIDS), vol. 5, 2024. doi: 10.11159/jmids.2024.012.