Prediksi Harga Emas Indonesia Menggunakan Model CNN-LSTM
DOI:
https://doi.org/10.23969/infomatek.v27i1.24417Keywords:
CNN-LSTM, Epoch, Root Mean Square Error, Data historis, Prediksi Harga EmasAbstract
Harga emas memiliki volatilitas tinggi yang menjadikannya menarik untuk dianalisis secara prediktif. Penelitian ini bertujuan untuk memprediksi harga emas Indonesia dengan kombinasi model Convolutional Neural Network dan Long Short-Term Memory (CNN-LSTM) berdasarkan data historis yang berjumlah 4.434 data dari PT Antam Tbk dari periode 2010 sampai 2025. Model ini dibangun menggunakan lapisan Conv1D (satu dimensi) untuk ekstraksi fitur dan dua lapisan LSTM untuk memahami pola waktu. Pengujian dilakukan dengan tiga variasi jumlah epoch pelatihan, yaitu 50, 100, dan 150, lalu hasilnya dievaluasi menggunakan metrik Root Mean Square Error (RMSE). Model terbaik ditemukan pada epoch 100 dengan nilai RMSE data pelatihan sebesar 5.811,51 dan data uji sebesar 13.236,10. Hasil ini menunjukkan bahwa model CNN-LSTM mampu mengenali pola harga emas lebih baik dibandingkan skenario lain. Dengan demikian, penelitian ini dapat dimanfaatkan untuk membantu para investor dalam mengambil keputusan investasi dan sebagai dasar pengembangan sistem prediksi harga komoditas lainnya.Downloads
References
Abbas. (2025). Dataset Harga Emas.
Alhamdani, F. D. S., Marthasari, G. I., & Aditya, C. S. K. (2021). Prediksi Harga Emas Menggunakan Metode Time Series Long Short-Term Memory Neural Network. REPOSITOR, 3(4), 375–386. https://eprints.umm.ac.id/id/eprint/5942
Amini, A., & Kalantari, R. (2024). Gold price prediction by a CNN-Bi-LSTM model along with automatic parameter tuning. PLoS ONE, 19(3 March). https://doi.org/10.1371/journal.pone.0298426
Asnawi, F., Bisono, H., Megantara, A., & Kusrini. (2023). Aplikasi Prediksi Banjir Menggunakan Algoritma XGBoost Berbasis Website. Journal of Economic, Management, Accounting and Technology, 379–389. http://dx.doi.org/10.32500/jematech.v7i2.7644
Billah, M. M., & Das, S. (2021). Analysis and Prediction of Gold Price using CNN and Bi-GRU based Neural Network Model. 24th International Conference on Computer and Information Technology, ICCIT 2021. https://doi.org/10.1109/ICCIT54785.2021.9689880
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
Fitriyanto, N., & Kusrini, K. (2025). Optimasi Prediksi Harga Emas Menggunakan CNN-Bi-LSTM dengan Mekanisme Attention dan Bayesian Optimization. Journal of Economic, Management, Accounting and Technology, 8(1), 210–219. https://doi.org/10.32500/jematech.v8i1.8668
Guridno, C., Azimah, A., & Ningsih, S. (2024). Jurnal Sistem Informasi Bisnis ( JUNSIBI) ANALISIS HYBRID METODE CNN DAN LSTM DALAM MEDIA BERITA ONLINE INDONESIA PENULIS 1). 5(1), 86–101. https://doi.org/10.55122/junsibi.v5i1.1202
Handayani, S., Taslim, & Toresa, D. (2022). Convolutional Neural Network Long Short Term Memory Untuk Prediksi Harga Emas Indonesia. Indonesian Journal of Computer Science. https://doi.org/https://doi.org/10.33022/ijcs.v11i3.3074
Julianto, M. F., Iqbal, M., Hidayat, W. F., & Malau, Y. (2024). PERBANDINGAN PENERAPAN ALGORITMA DEEP LEARNING DALAM PREDIKSI HARGA EMAS. INTI Nusa Mandiri, 19(1), 71–76. https://doi.org/10.33480/inti.v19i1.5559
Liang, Y., Lin, Y., & Lu, Q. (2022). Forecasting gold price using a novel hybrid model with ICEEMDAN and LSTM-CNN-CBAM. Expert Systems with Applications, 206, 117847. https://doi.org/10.1016/J.ESWA.2022.117847
Purwanti, Y. (2022). Analysis of the Influence of Gold Price, Rupiah Exchange Rate and Interest Rate on West Java Inflation Persistence Degrees. 1(1), 43–52. https://doi.org/10.21787/govstat.1.1.2022.43-52
Qiu, C., Zhang, Y., Qian, X., Wu, C., Lou, J., Chen, Y., Xi, Y., Zhang, W., & Gong, Z. (2024). A Two-stage Deep Fusion Integration Framework Based on Feature Fusion and Residual Correction for Gold Price Forecasting. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3408837
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
Santika, I. W. K. G., Sa’adah, S., & Yunanto, P. E. (2021). Prediksi harga emas menggunakan Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM). Universitas Telkom, S1 Informatika. https://repository.telkomuniversity.ac.id/pustaka/172951/prediksi-harga-emas-menggunakan-convolutional-neural-network-long-short-term-memory-cnn-lstm-.html
Sezer, O. B., Gudelek, M. U., & Ozbayoglu, A. M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied Soft Computing Journal, 90. https://doi.org/10.1016/j.asoc.2020.106181
Tholib, A., Agusmawati, N. K., & Khoiriyah, F. (2023). PREDIKSI HARGA EMAS MENGGUNAKAN METODE LSTM DAN GRU. Jurnal Informatika Dan Teknik Elektro Terapan, 11(3). https://doi.org/10.23960/jitet.v11i3.3250
Vidal, A., & Kristjanpoller, W. (2020). Gold volatility prediction using a CNN-LSTM approach. Expert Systems with Applications, 157. https://doi.org/10.1016/j.eswa.2020.113481
Yan, W., & Elbushra, M. (2024). Forecasting Sudan Gold Prices with a Hybrid Deep Learning Approach. 2024 International Conference on Cloud and Network Computing (ICCNC), 71–78. https://doi.org/10.1109/ICCNC63989.2024.00020
Yao, J., Wang, J., Wang, B., Liu, B., & Jiang, M. (2024). A Hybrid CNN-LSTM Model for Enhancing Bond Default Risk Prediction. https://ashpress.org/index.php/jcts/article/view/79/56
Zhang, J., & Lei, Y. (2022). Deep Reinforcement Learning for Stock Prediction. Scientific Programming, 2022. https://doi.org/10.1155/2022/5812546
