Optimasi Prediksi Harga Emas Menggunakan CNN-Bi-LSTM dengan Mekanisme Attention dan Bayesian Optimization
CNN-Bi-LSTM, Attention, Bayesian Optimization, Prediksi Harga Emas, Time Series
Abstract
Prediksi harga emas merupakan aspek penting dalam investasi global karena volatilitasnya yang dipengaruhi oleh faktor ekonomi dan politik. Penelitian ini mengembangkan model hybrid CNN-Bi-LSTM dengan mekanisme Attention untuk menangkap pola data signifikan dan Bayesian Optimization untuk pencarian hyperparameter yang lebih efisien. Dataset yang digunakan mencakup harga emas harian dari 29 Desember 1978 hingga 4 Juni 2021, yang terbagi menjadi data pelatihan (70%), validasi (20%), dan pengujian (10%). Model yang dioptimasi menunjukkan hasil evaluasi dengan RMSE sebesar 17,98, MAE sebesar 10,93, RMAE sebesar 3,31, dan R² sebesar 1,00. Visualisasi hasil menunjukkan konvergensi stabil tanpa overfitting, distribusi residual yang mendekati normal, serta prediksi yang konsisten dengan data aktual. Integrasi mekanisme Attention dan Bayesian Optimization terbukti meningkatkan performa model secara signifikan. Penelitian ini membuka peluang pengembangan lebih lanjut dengan memasukkan variabel makroekonomi tambahan, seperti harga minyak mentah atau indeks saham, untuk memperluas cakupan prediksi.
Downloads
References
Boongasame, L., Viriyaphol, P., Tassanavipas, K., & Temdee, P. (2023). Gold-Price Forecasting Method Using Long Short-Term Memory and the Association Rule. Journal of Mobile Multimedia, 19(1), 165–186. https://doi.org/10.13052/jmm1550-4646.1919
Ding, S., Ding, S., & Ding, T. (2023). Trading strategy prediction model based on quadratic programming and XGBoost. Proceedings - 2023 Asia-Europe Conference on Electronics, Data Processing and Informatics, ACEDPI 2023, 165–170. https://doi.org/10.1109/ACEDPI58926.2023.00040
Gong, W. (2024). Research on gold price forecasting based on lstm and linear regression. SHS Web of Conferences, 181, 02005. https://doi.org/10.1051/shsconf/202418102005
Hansun, S., & Suryadibrata, A. (2021). Gold price prediction in covid-19 era. International Journal of Computational Intelligence in Control, 13(2), 29–34.
Huang, Y., Yang, M., & Wang, L. (2024). Gold Price Prediction Model Based on LSTM Neural Network and ARIMA. Highlights in Science, Engineering and Technology, 101, 904–913. https://doi.org/10.54097/zpxfzc86
Lei, J., & Lin, Q. (2022). Analysis of gold and bitcoin price prediction based on LSTM model. Academic Journal of Computing & Information Science, 5(6), 95–100. https://doi.org/10.25236/ajcis.2022.050614
Mohtasham Khani, M., Vahidnia, S., & Abbasi, A. (2021). A Deep Learning-Based Method for Forecasting Gold Price with Respect to Pandemics. SN Computer Science, 2(4), 1–12. https://doi.org/10.1007/s42979-021-00724-3
Primananda, S. B., & Isa, S. M. (2021). Forecasting Gold Price in Rupiah using Multivariate Analysis with LSTM and GRU Neural Networks. Advances in Science, Technology and Engineering Systems Journal, 6(2), 245–253. https://doi.org/10.25046/aj060227
Salim, M., & Djunaidy, A. (2024). Development of a CNN-LSTM Approach with Images as Time-Series Data Representation for Predicting Gold Prices. Procedia Computer Science, 234, 333–340. https://doi.org/10.1016/j.procs.2024.03.007
Sivasamy, R. (2024). Machine Learning-Based GRU, LSTM, HMM, and SARIMA Models for Gold Pricing. Journal of Electrical Systems, 20(10s), 215–227. https://www.proquest.com/scholarly-journals/machine-learning-based-gru-lstm-hmm-sarima-models/docview/3092061935/se-2?accountid=49910%0Ahttps://media.proquest.com/media/hms/PFT/1/VXdTZ?_a=ChgyMDI0MDkxNTA2MTIxNDQ3NzoxMzkxNjgSBTMzNDM4GgpPTkVfU0VBUkNIIg02Ni4
World Gold Council. (n.d.). Regional Diversity of Gold Demand. https://www.gold.org/about-gold
YURTSEVER, M. (2021). Gold Price Forecasting Using LSTM, Bi-LSTM and GRU. European Journal of Science and Technology, 31(31), 341–347. https://doi.org/10.31590/ejosat.959405
Zhang, X., Zhang, L., Zhou, Q., & Jin, X. (2022). A Novel Bitcoin and Gold Prices Prediction Method Using an LSTM-P Neural Network Model. Computational Intelligence and Neuroscience, 2022. https://doi.org/10.1155/2022/1643413
