HYBRID DEEP NEURAL NETWORK WITH ATTENTION FOR MONTHLY GOLD PRICE FORECASTING

Oktavia Mulyo Nurdiyanti, Giat Karyono, Berlilana Berlilana

Abstract


Fluktuasi harga emas yang tinggi dari waktu ke waktu mendorong perlunya pengembangan model prediksi yang andal untuk membantu investor dalam pengambilan keputusan. Penelitian ini bertujuan untuk membangun model prediksi harga emas bulanan menggunakan pendekatan hybrid deep learning yang meng-gabungkan Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), dan Attention Mechanism. Dataset yang digunakan adalah data historis harga emas periode 2013–2023 yang telah diproses menjadi data bulanan dan dinormal-isasi. Proses pelatihan dilakukan dengan konfigurasi hyperparame-ter optimal hasil grid search, yaitu learning rate 0.001, batch size 16, dan epoch 3000. Model dievaluasi menggunakan metrik MAE, RMSE, MAPE, akurasi, dan koefisien determinasi. Hasil evaluasi menunjukkan bahwa model mencapai RMSE sebesar 53.78, MAE sebesar 39.11, MAPE sebesar 2.78%, akurasi prediksi sebesar 97.22%, dan R² sebesar 0.9602. Model mampu mengikuti tren fluktuasi harga emas bulanan dengan tingkat ketepatan yang tinggi. Integrasi CNN, BiLSTM, dan Attention terbukti meningkatkan kinerja prediktif dibandingkan pendekatan konvensional. Dengan demikian, model ini berpotensi menjadi alat bantu yang efektif dalam meramalkan harga emas dan mendukung pengambilan keputusan investasi berbasis data

Keywords


prediksi harga emas; CNN; BiLSTM; atten-tion mechanism; deep learning

Full Text:

PDF

References


V. Riandaru Prasetyo et al., “SISTEMASI: Jurnal Sistem Informasi Prediksi Harga Emas Berdasarkan Data gold.org menggunakan Metode Long Short Term Memory Gold Price Prediction Based on Gold.org Data using the Long Short Term Memory Method.” [Online]. Available: http://sistemasi.ftik.unisi.ac.id

M. Nurul Taukid et al., “IMPLEMENTASI BILSTM DAN CUCKOO SEARCH OPTIMIZATION PADA APLIKASI PREDIKSI HARGA EMAS ANTAM,” 2025.

C. Tanudy, T. Handhayani, and J. Hendryli, “Prediksi Harga Emas di Indonesia Menggunakan Gated Recurrent Unit”.

Y. Liang, Y. Lin, and Q. Lu, “Forecasting gold price using a novel hybrid model with ICEEMDAN and LSTM-CNN-CBAM,” Expert Syst Appl, vol. 206, Nov. 2022, doi: 10.1016/j.eswa.2022.117847.

I. Halimi, Y. Azhar, and G. I. Marthasari, “Prediksi Harga Emas Menggunakan Univariate Convolutional Neural Network,” vol. 1, no. 2, pp. 105–116, 2019.

A. Tholib, N. K. Agusmawati, and F. Khoiriyah, “PREDIKSI HARGA EMAS MENGGUNAKAN METODE LSTM DAN GRU,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 11, no. 3, Aug. 2023, doi: 10.23960/jitet.v11i3.3250.

A. P. Meriani and A. Rahmatulloh, “PERBANDINGAN GATED RECURRENT UNIT (GRU) DAN ALGORITMA LONG SHORT TERM MEMORY (LSTM) LINEAR REFRESSION DALAM PREDIKSI HARGA EMAS MENGGUNAKAN MODEL TIME SERIES,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 1, Jan. 2024, doi: 10.23960/jitet.v12i1.3808.

M. Mushliha, “Implementasi CNN-BiLSTM untuk Prediksi Harga Saham Bank Syariah di Indonesia,” Jambura Journal of Mathematics, vol. 6, no. 2, pp. 195–203, Aug. 2024, doi: 10.37905/jjom.v6i2.26509.

S. Handayani, Taslim, and Toresa, “Convolutional Neural Network –Long Short Term Memory Untuk Prediksi Harga Emas Indonesia,” vol. 2022.

L. Shan, Y. Liu, M. Tang, M. Yang, and X. Bai, “CNN-BiLSTM hybrid neural networks with attention mechanism for well log prediction,” J Pet Sci Eng, vol. 205, Oct. 2021, doi: 10.1016/j.petrol.2021.108838.

J. Zhang, L. Ye, and Y. Lai, “Stock Price Prediction Using CNN-BiLSTM-Attention Model,” Mathematics, vol. 11, no. 9, May 2023, doi: 10.3390/math11091985.

A. Amini and R. Kalantari, “Gold price prediction by a CNN-Bi-LSTM model along with automatic parameter tuning,” PLoS One, vol. 19, no. 3 March, Mar. 2024, doi: 10.1371/journal.pone.0298426.

S. Y. Shih, F. K. Sun, and H. yi Lee, “Temporal pattern attention for multivariate time series forecasting,” Mach Learn, vol. 108, no. 8–9, pp. 1421–1441, Sep. 2019, doi: 10.1007/s10994-019-05815-0.

X. Ran, Z. Shan, Y. Fang, and C. Lin, “An LSTM-based method with attention mechanism for travel time prediction,” Sensors (Switzerland), vol. 19, no. 4, Feb. 2019, doi: 10.3390/s19040861.

S. Chen and L. Ge, “Exploring the attention mechanism in LSTM-based Hong Kong stock price movement prediction,” Quant Finance, vol. 19, no. 9, pp. 1507–1515, 2019, doi: 10.1080/14697688.2019.1622287.

S. Kitada and H. Iyatomi, “Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training,” IEEE Access, vol. 9, pp. 92974–92985, 2021, doi: 10.1109/ACCESS.2021.3093456.

J. Kim et al., “Limitations of deep learning attention mechanisms in clinical research: Empirical case study based on the Korean diabetic disease setting,” J Med Internet Res, vol. 22, no. 12, Dec. 2020, doi: 10.2196/18418.

J. Liu, J. Yang, K. Liu, and L. Xu, “Ocean Current Prediction Using the Weighted Pure Attention Mechanism,” J Mar Sci Eng, vol. 10, no. 5, May 2022, doi: 10.3390/jmse10050592.

A. Hernández and J. M. Amigó, “Attention mechanisms and their applications to complex systems,” Entropy, vol. 23, no. 3, pp. 1–18, Mar. 2021, doi: 10.3390/e23030283.

X. Wang, “CNN-BiLSTM-Attention Algorithm-Based Stock Prices Prediction During COVID-19,” 2024, pp. 441–452. doi: 10.2991/978-94-6463-512-6_47.

S. Sun, J. Sun, Z. Wang, Z. Zhou, and W. Cai, “Prediction of Battery SOH by CNN-BiLSTM Network Fused with Attention Mechanism,” Energies (Basel), vol. 15, no. 12, Jun. 2022, doi: 10.3390/en15124428.

I. E. Livieris, E. Pintelas, and P. Pintelas, “A CNN–LSTM model for gold price time-series forecasting,” Neural Comput Appl, vol. 32, no. 23, pp. 17351–17360, Dec. 2020, doi: 10.1007/s00521-020-04867-x.

Z. He, J. Zhou, H.-N. Dai, and H. Wang, Gold Price Forecast based on LSTM-CNN Model. IEEE, 2019.




DOI: https://doi.org/10.29100/jipi.v11i2.8219

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika)
ISSN 2540-8984
Published by
Prodi Pendidikan Teknologi Informasi
Universitas Bhinneka PGRI

Website :https://jurnal.stkippgritulungagung.ac.id/index.php/jipi/index
Email: jipistkippti@gmail.com

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.