Optimasi Hiperparameter Extreme Learning Machine Menggunakan Particle Swarm Optimization dan Indikator Teknikal untuk Peramalan Bitcoin

Bagus Putra Sulung; Wiwit Agus Triyanto; Pratomo Setiaji

doi:10.36080/idealis.v9i2.3812

Authors

Bagus Putra Sulung Sistem Informasi, Fakultas Teknik, Universitas Muria Kudus, Kudus, Indonesia
Wiwit Agus Triyanto Sistem Informasi, Fakultas Teknik, Universitas Muria Kudus, Kudus, Indonesia
Pratomo Setiaji Sistem Informasi, Fakultas Teknik, Universitas Muria Kudus, Kudus, Indonesia

DOI:

https://doi.org/10.36080/idealis.v9i2.3812

Keywords:

Bitcoin, Extreme Learning Machine, Particle Swarm Optimization, Price Forecasting, Technical Indicator

Abstract

Highly volatile price changes in crypto assets like Bitcoin complicate precise forecasting. The Extreme Learning Machine (ELM) artificial neural network approach offers high computational speed but is prone to performance instability due to random weight initialization and manual hyperparameter determination. To overcome this problem, this study proposes a hybrid PSO-ELM algorithm to automate the search for optimal parameters, namely the number of hidden neurons and the regression regularization penalty. Evaluated using a five-fold Walk-Forward Validation to prevent data leakage, the model comparatively tested five input feature scenarios based on technical indicators, which are mathematical calculations from historical prices to identify market patterns. Results demonstrate the hybrid PSO-ELM outperforms conventional static models, reducing average error (MAPE) by 18.67 percent. The cross-scenario comparison reveals that applying the Simple Moving Average technical indicator yields the best forecasting model, achieving a 26.65 percent error reduction and a final MAPE accuracy of 2.15 percent. The contribution of this research is providing empirical evidence that automatic parameter optimization combined with a random fluctuation filtering feature is proven to be more robust and accurate in responding to extreme volatility compared to the stacking of various complex derivative momentum indicators.

Downloads

Download data is not yet available.

References

[1] J. Tarassov and N. Houlie, “Bitcoin: A life in crises,” PLoS One, vol. 17, no. 9, pp. 1–16, 2022, doi: 10.1371/journal.pone.0274165.

[2] D. Widyanti, Sudarno, and T. Widiharih, “Analisis volatilitas Bitcoin menggunakan model ARCH dan GARCH,” J. GAUSSIAN, vol. 12, no. 2, pp. 254–265, 2023, doi: 10.14710/J.GAUSS.12.2.254-265.

[3] K. Koszewski, S. Mazumdar, and A. S. Kumar, “Understanding rate of return dynamics of cryptocurrencies: An experimental campaign,” Artif. Intell. Rev., vol. 57, no. 8, pp. 1–29, 2024, doi: 10.1007/s10462-023-10629-7.

[4] P. Hiskiawan, J. William, L. Feliepe, and T. Jansel, “A hybrid data science framework for forecasting Bitcoin prices using traditional and AI models,” J. Appl. Informatics Comput., vol. 9, no. 5, pp. 2089–2101, 2025.

[5] R. F. T. Wulandari and D. Anubhakti, “Implementasi algoritma support vector machine (SVM) dalam memprediksi harga saham PT. Garuda Indonesia Tbk.,” IDEALIS Indones. J. Inf. Syst., vol. 4, no. 2, pp. 250–256, 2021.

[6] R. Ilmiyah, D. Rachmatin, and R. Marwati, “Peramalan inflasi dengan metode particle swarm optimization – extreme learning machine,” INTERVAL J. Ilm. Mat., vol. 2, no. 1, pp. 42–51, 2022.

[7] M. F. S, S. Annas, and N. Ismi, “Penerapan extreme learning machine (ELM) untuk meramalkan laju inflasi di Indonesia,” VARIANSI J. Stat. Its Appl. Teach. Res., vol. 6, no. 3, pp. 119–129, 2024, doi: 10.35580/variansiunm92.

[8] I. Pratiwi, D. Bachtiar, A. Jauhari, M. Yusuf, F. A. Mufarroha, and D. Rosa, “Extreme learning machine untuk memprediksi curah hujan dalam penentuan jadwal tanam padi,” JUSIFOR J. Sist. Inf. dan Inform., vol. 4, no. 1, pp. 34–42, 2024.

[9] A. Kenioua, O. Djebili, and A. Touati, “Hybrid extreme learning machine for real-time rate of penetration prediction,” J. Pet. Explor. Prod. Technol., vol. 15, no. 139, pp. 1–21, 2025.

[10] A. P. Ariyanti, M. I. Mazdadi, A. Farmadi, Muliadi, and R. Herteno, “Application of extreme learning machine method with particle swarm optimization to classify of heart disease,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 17, no. 3, pp. 281–290, 2023.

[11] P. Setiaji et al., “Best model and performance of Bayesian regularization method for data prediction,” J. Phys. Conf. Ser., vol. 1933, no. 1, p. 012030, 2021, doi: 10.1088/1742-6596/1933/1/012030.

[12] Q. Lin and M. Wang, “Temperature characteristics modeling for GaN PA based on PSO-ELM,” micromachines, vol. 15, no. 1008, pp. 1–15, 2024.

[13] N. Farhana, G. F. Hertono, and B. D. Handari, “Classification of coal mine pillar stability using extreme learning machine and particle swarm optimization adaptive klasifikasi kestabilan pilar tambang batu bara menggunakan extreme learning machine dan particle swarm optimization adaptive weight delay,” J. Tek. Inform., vol. 5, no. 6, pp. 1569–1580, 2024.

[14] Z. Adel, “A comparative study between RSI and MACD to predict opportunities in cryptocurrency market from 2020 to 2022,” J. Econ. Sci. Inst., vol. 26, no. 2, pp. 195–214, 2023.

[15] W. G. Mokodaser, H. P. Koapaha, and S. I. Adam, “Model random forest data historis multivariat untuk prediksi pendapatan asuransi,” IDEALIS Indones. J. Inf. Syst., vol. 8, no. 2, pp. 267–276, 2025.

[16] T. Astutiningsih, D. R. S. Saputro, and Sutanto, “Optimasi algoritme xtreme gradient boosting (XGBoost) pada harga saham PT. United Tractors Tbk.,” SPECTA J. Technol., vol. 7, no. 3, pp. 632–641, 2023, doi: 10.35718/specta.v7i3.1031.

[17] W. M. P. Dhuhita and Y. I. Sumbadri, “Analysis of LSTM-Adamax performance in Bitcoin price prediction using RSI & MACD indicators,” IJCSR Indones. J. Comput. Sci. Res., vol. 5, no. 1, pp. 68–78, 2026.

[18] A. Baradja, Sukoco, and T. I. Tjendrowasono, “Penerapan machine learning untuk meningkatkan prediksi mata uang forex dengan indikator teknikal,” J. Pustaka AI, vol. 2, no. 1, pp. 38–41, 2023.

[19] M. M. R. Musyaffa, G. F. Hertono, and B. D. Handari, “Implementation of moving average filter in SARIMA-ANN and SARIMA-SVR methods for forecasting pneumonia incidence in Jakarta,” JAMBURA J. Biomath., vol. 6, no. 3, pp. 262–269, 2025.

[20] T. Liu, “A comparative study of transformer-based and classical models for financial time-series forecasting,” J. Risk Financ. Manag., vol. 19, no. 203, pp. 1–16, 2026.

[21] P. Yanida, L. N. Pratiwi, and W. P. Nugrahani, “Comparative evaluation of portfolio performance: A study of cryptocurrency, stock, and foreign exchange investments,” J. Ilmu Keuang. dan Perbank., vol. 13, no. 1, pp. 45–62, 2023.

[22] E. M. C. Wattimena, P. D. M. Taihuttu, D. V. Waas, C. F. Palembang, and V. E. Pattiradjawane, “Optimasi model LSTM untuk prediksi curah hujan di Kota Ambon: Perbandingan mean imputation dan interpolasi dalam prediksi data time series,” Tensor Pure Appl. Math. J., vol. 6, no. 1, pp. 49–56, 2025.

[23] R. Parlika, I. Asy’ari, and R. A. Ramadhan, “Predicting Bitcoin price trends using an LSTM model based on multi-variable technical indicators,” J. Serumpun Tek. Inform., vol. 1, no. 2, pp. 59–66, 2026.

[24] P. J. Muhammad and Ali, “Investigating the impact of min-max data normalization on the regression performance of k-nearest neighbor with different similarity measurements,” ARO-The Sci. J. Koya Univ., vol. 10, no. 1, pp. 85–91, 2022, doi: 10.14500/aro.10955.

[25] X. Liu, G. Zhou, Y. Zhou, and Q. Luo, “Functional extreme learning machine,” Front. Comput. Neurosci., vol. 17, p. 1209372, 2023, doi: 10.3389/fncom.2023.1209372.

[26] K. C. Pradhisa and R. Yotenka, “Penerapan metode extreme learning machine (ELM) untuk meramalkan produksi air minum dan air yang dijual di Kota Yogyakarta tahun 2023,” Emerg. Stat. Data Sci. J., vol. 2, no. 2, pp. 258–263, 2024.

[27] X. Fang et al., “Equipment remaining useful life prediction algorithm based on hyperparameter optimization and LSTM,” AIP Adv., vol. 16, no. 4, p. 045013, 2026, doi: 10.1063/5.0327489.

[28] T. Nagamani, G. V. Gopal, G. Lakshmi, K. V. S. S. Ramakrishna, N. Srija, and A. Gopi, “Improving model robustness against multicollinearity with a novel statistical regularized extreme learning algorithm,” IAENG Int. J. Comput. Sci., vol. 52, no. 11, pp. 4301–4309, 2025.

[29] S. Aisyah, N. Ulinnuha, and A. Hamid, “Penerapan extreme learning machine dalam meramalkan harga minyak sawit mentah,” KUBIK J. Publ. Ilm. Mat., vol. 7, no. 2, pp. 97–105, 2022.