Comparative Deep Learning Models for Indonesian Gold Price Forecasting
DOI:
https://doi.org/10.26877/asset.v8i3.2608Keywords:
Bayesian optimization, deep learning, gold price forecasting, LSTM-GRU, time-series predictionAbstract
This study evaluates LSTM, CNN-LSTM, LSTM-GRU, and CNN-LSTM-GRU architectures for forecasting Indonesian gold prices using 1,269 daily observations (2022–2025). Models utilized Bayesian-optimized hyperparameters and were benchmarked against ARIMA-GARCH and Random Forest baselines across 30-day and 365-day horizons. Performance was assessed via MAE, RMSE, R², and MAPE, confirming deep learning’s superiority in capturing non-linear dynamics over classical methods. The LSTM-GRU achieved the best numerical results, with MAPEs of 1.21% (short-term) and 1.32% (long-term). However, qualitative evaluation revealed that the highest-scoring model produced unstable long-term predictions, indicating a critical trade-off between numerical accuracy and forecast realism. These findings suggest financial model selection must prioritize stability alongside statistical metrics. A key limitation is the exclusive use of univariate data, necessitating future multivariate validation with macroeconomic indicators.
References
[1] H. D. Fadly and F. Arifin, "Indonesian Gold Price Prediction: A Machine Learning Approach Using Random Forest Regressor," Int. J. Comput. Sci. Mobile Comput., vol. 14, no. 2, pp. 32–43, Feb. 2025. DOI: https://doi.org/10.47760/ijcsmc.2025.v14i02.004
[2] M. Mokashi et al., "A Comparative Analysis of Long Short-Term Memory Networks and Artificial Neural Networks for Gold Price Prediction," J. Inf. Syst. Eng. Manag., vol. 10, no. 34s, 2025.
[3] N. K. Saikumar et al., “Enhanced air quality prediction using AI: A comparative study of GRU, CNN, and XGBoost models,” Adv. Sustain. Sci. Eng. Technol., vol. 7, no. 3, Art. no. 02503012, Jun. 2025. DOI: https://doi.org/10.26877/asset.v7i3.1589
[4] I. D. Raharjo and N. E. R. Subhiyakto, “Implementing long short-term memory (LSTM) in chatbots for Multi Usaha Raya,” Adv. Sustain. Sci. Eng. Technol., vol. 6, no. 4, Art. no. 02404018, Oct. 2024. DOI: https://doi.org/10.26877/asset.v6i4.934
[5] L. Gasper and H. Mbwambo, “Forecasting Crude Oil Prices by Using ARIMA Model: Evidence from Tanzania,” Journal of Accounting, Finance and Auditing Studies, vol 9, no. 2, 2023. DOI: https://doi.org/10.32602/jafas.2023.017
[6] L. K. Shrivastav and R. Kumar, “An ensemble of random forest gradient boosting machine and deep learning methods for stock price prediction”, Journal of Information Technology Research (JITR), vol. 15 no. 1. 2022. DOI: https://doi.org/10.4018/JITR.2022010102
[7] S. Setyowibowo, M. As’ad, S. Sujito, and E. Farida, “Forecasting of Daily Gold Price Using ARIMA–GARCH Hybrid Model,” J. Ekonomi Pembangunan, vol. 19, no. 2, pp. 257–270, 2022. DOI: https://doi.org/10.29259/jep.v19i2.13903
[8] Y. Luo, "A Research of Fine-Tuning CNN-LSTM Model for Gold Price Prediction," Proc. Finance in the Age of Environmental Risks and Sustainability - ICFTBA, 2024. DOI: https://doi.org/10.54254/2754-1169/94/2024ox0185
[9] Y. Guo, " Research on the application of gold price prediction based on LSTM mode," Information Systems and Economics, vol. 5 no.4, 2024. DOI: 10.23977/infse.2024.050414
[10] Z. Wang, J. Yan, and H. O. Wang, “Deep learning for time series forecasting: A survey,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 11, pp. 4761–4783, 2021. DOI: https://doi.org/10.1109/ACCESS.2024.3422528
[11] “Current gold prices in Indonesian rupiahs (IDR).” Bullion-Rates.com, [Online]. Available: https://www.bullion-rates.com. [Accessed: Jun. 2025].
[12] S. Livieris, G. Pintelas, and P. Pintelas, “A CNN–LSTM model for gold price time-series forecasting,” Neural Computing and Applications, vol. 33, pp. 13559–13568, 2021. DOI: https://doi.org/10.1007/s00521-020-04867-x
[13] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. Melbourne, Australia: OTexts, 2021. [Online]. Available: https://otexts.com/fpp3/
[14] A. Amini and M. Kalantari, “Gold price prediction by a CNN-Bi-LSTM model along with automatic parameter tuning,” PlosOne, Mar 7;19(3):e0298426, 2024. DOI: https://doi.org/10.1371/journal.pone.0298426
[15] H. Fischer and B. Krauss, “Deep learning with long short-term memory networks for financial market predictions,” European Journal of Operational Research, vol. 270, no. 2, pp. 654–669, 2018. DOI: https://doi.org/10.1016/j.ejor.2017.11.054
[16] Y. Zhang, M. Liu, and S. X. Yang, “Time series forecasting using a hybrid ARIMA and neural network model,” Neurocomputing, vol. 50, pp. 159–175, 2003. DOI: https://doi.org/10.1016/S0925-2312(01)00702-0
[17] J. Brownlee, “How to Convert a Time Series to a Supervised Learning Problem in Python,” Machine Learning Mastery, [Online]. Available: https://machinelearningmastery.com/convert-time-series-supervised-learning-problem-python/ . [Accessed: Jul. 2, 2025].
[18] Y. Kim and H. Kim, “Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data,” PLOS ONE, vol. 16, no. 6, p. e0252313, 2021. https://doi.org/10.1371/journal.pone.0212320
[19] I. W. K. G, Santika, S. Sa'adah, and P. E. Yunanto, “Gold price prediction using convolutional neural network-long short-term memory (CNN-LSTM)”, Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, vol. 6 no. 3, 2021.DOI: https://doi.org/10.22219/kinetik.v6i3.1253
[20] N. Rouf, M. B. Malik, T. Arif, S. Sharma, S. Singh, S. Aich, and H. C. Kim, “Stock market prediction using machine learning techniques: a decade survey on methodologies, recent developments, and future directions”, Electronics, vol.10 no. 21, 2717, 2021. DOI: https://doi.org/10.3390/electronics10212717
[21] G. R. Patra and M. N. Mohanty,” An LSTM-GRU based hybrid framework for secured stock price prediction”, Journal of Statistics and Management Systems, vol. 25 no. 6, 2022. DOI: https://doi.org/10.1080/09720510.2022.2092263
[22] W. Fu,” Financial Time Series Data Forecasting based on CEEMDAN-BiGRU-BO Model”, Frontiers in Economics and Management, vol. 6 no. 12, 90-105. 2025. DOI: https://doi.org/10.6981/FEM.202512_6(12).0008
[23] G. Taneva-Angelova, S. Raychev, and G. Ilieva, “A framework for gold price prediction combining classical and intelligent methods with financial, economic, and sentiment data fusion,” International Journal of Financial Studies, vol. 13, no. 2, p. 102, 2025. DOI: https://doi.org/10.3390/ijfs13020102
[24] G. S., Vidya and V. S.Hari, “Gold price prediction and modelling using deep learning techniques”, In 2020 IEEE Recent Advances in Intelligent Computational Systems (RAICS) (pp. 28-31). IEEE. 2020. DOI: https://doi.org/10.1109/RAICS51191.2020.9332471
[25] J. Bergstra, R. Bardenet, Y. Bengio, and B. Kégl, “Algorithms for hyper-parameter optimization,” in Advances in Neural Information Processing Systems, vol. 24, 2011.
[26] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” in Proc. of the 3rd International Conference on Learning Representations (ICLR), 2015. [Online]. Available: https://arxiv.org/abs/1412.6980
[27] T. Dozat, “Incorporating Nesterov Momentum into Adam,” ICLR Workshop, 2016. [Online]. Available: https://openreview.net/forum?id=OM0jvwB8jIp57ZJjtNEZ
[28] T. Tieleman and G. Hinton, “Lecture 6.5 - RMSProp: Divide the gradient by a running average of its recent magnitude,” COURSERA: Neural Networks for Machine Learning, 2012.
[29] L. Bottou, “Large-scale machine learning with stochastic gradient descent,” in Proceedings of COMPSTAT, Heidelberg: Physica-Verlag HD, pp. 177–186. 2010. DOI: https://doi.org/10.1007/978-3-7908-2604-3_16
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Advance Sustainable Science Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
