Perbandingan Performa Algoritma ARIMA, XGBoost, dan LSTM untuk Prediksi Harga Bitcoin Menggunakan Dataset Publik
DOI:
https://doi.org/10.58344/jii.v5i7.7957Keywords:
Bitcoin, Prediksi Harga, ARIMA, XGBoost, LSTM.Abstract
Bitcoin merupakan aset digital berbasis teknologi blockchain yang memiliki karakteristik volatilitas harga tinggi sehingga menyulitkan proses pengambilan keputusan investasi dan meningkatkan kebutuhan akan metode prediksi yang akurat. Seiring meningkatnya adopsi Bitcoin dan transaksi aset kripto di Indonesia, kemampuan memprediksi pergerakan harga menjadi semakin penting bagi investor maupun pelaku industri. Meskipun berbagai penelitian telah mengembangkan model prediksi harga cryptocurrency, kajian komparatif yang membandingkan pendekatan statistik, machine learning, dan deep learning pada dataset yang sama masih terbatas. Oleh karena itu, penelitian ini bertujuan untuk membandingkan performa algoritma Autoregressive Integrated Moving Average (ARIMA), Extreme Gradient Boosting (XGBoost), dan Long Short-Term Memory (LSTM) dalam memprediksi harga harian Bitcoin. Dataset yang digunakan berupa data historis Bitcoin terhadap Rupiah (BTC/IDR) periode 1 Januari 2020 hingga 31 Mei 2025 yang diperoleh dari dataset publik. Tahapan penelitian meliputi pengumpulan data, prapemrosesan data, pembagian data menggunakan metode temporal split dengan rasio 70:30, implementasi model baseline tanpa optimasi hyperparameter, serta evaluasi menggunakan metrik Root Mean Square Error (RMSE), Mean Absolute Error (MAE), dan Mean Absolute Percentage Error (MAPE). Hasil penelitian menunjukkan bahwa model LSTM menghasilkan performa terbaik dengan nilai RMSE sebesar 83.205.260, MAE sebesar 63.429.270, dan MAPE sebesar 4,90%, diikuti oleh XGBoost dengan nilai MAPE sebesar 20,29%, sedangkan ARIMA menghasilkan performa terendah dengan nilai MAPE sebesar 46,44%. Temuan ini menunjukkan bahwa LSTM lebih efektif dalam menangkap pola non-linear dan dependensi temporal pada data harga Bitcoin yang bersifat volatil dibandingkan ARIMA dan XGBoost. Dengan demikian, pendekatan deep learning menggunakan LSTM dapat menjadi alternatif yang lebih baik.
References
AlMadany, N. N., Hujran, O., Al Naymat, G., & Maghyereh, A. (2024). Forecasting cryptocurrency returns using classical statistical and deep learning techniques. International Journal of Information Management Data Insights, 4(2), 100251.
Batsi, A., Biniz, M., & El Ayachi, R. (2025). Forecasting bitcoin price fluctuations: a time series analysis approach for predictive modelling. Indonesian Journal of Electrical Engineering and Computer Science, 37(3), 1964. https://doi.org/10.11591/ijeecs.v37.i3.pp1964-1975
Chaudhary, D., & Saroj, S. K. (2023). Cryptocurrency price prediction using supervised machine learning algorithms. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, 12(1), e31490. https://doi.org/10.14201/adcaij.31490
Dudek, G., Fiszeder, P., Kobus, P., & Orzeszko, W. (2024). Forecasting cryptocurrencies volatility using statistical and machine learning methods: A comparative study. Applied Soft Computing, 151. https://doi.org/10.1016/j.asoc.2023.111132
Fawzi, M. I., Ganesha, T., Anugrah, P. R., Zhahran, M., Abimanyu, F. A., & Bimantoro, H. (2025). Forecasting Bitcoin price prediction with Long Short-Term Memory networks: Implementation and applications using Streamlit. Jurnal Teknik Informatika (JUTIF), 6(5), 2940–2961. https://doi.org/10.52436/1.jutif.2025.6.5.5168
Huang, Z.-C., Sangiorgi, I., & Urquhart, A. (2024). Forecasting Bitcoin volatility using machine learning techniques. Journal of International Financial Markets, Institutions and Money, 97, 102064. https://doi.org/10.1016/j.intfin.2024.102064
Jaquart, P., Köpke, S., & Weinhardt, C. (2022). Machine learning for cryptocurrency market prediction and trading. The Journal of Finance and Data Science, 8, 331–352. https://doi.org/10.1016/j.jfds.2022.12.001
Liu, Y., Li, Z., Nekhili, R., & Sultan, J. (2023). Forecasting cryptocurrency returns with machine learning. Research in International Business and Finance, 64, 101905. https://doi.org/10.1016/j.ribaf.2023.101905
Mizdrakovic, V., Kljajic, M., Zivkovic, M., Bacanin, N., Jovanovic, L., Deveci, M., & Pedrycz, W. (2024). Forecasting bitcoin: Decomposition aided long short-term memory based time series modeling and its explanation with Shapley values. Knowledge-Based Systems, 299. https://doi.org/10.1016/j.knosys.2024.112026
Nafkha, R., Suchodolska, D. ?., & Hoser, P. (2024). Machine Learning-Based Volatility Prediction Performance. Procedia Computer Science, 246, 2665–2674. https://doi.org/10.1016/j.procs.2024.09.407
Nakamoto, S. (n.d.). Bitcoin: A Peer-to-Peer Electronic Cash System. Retrieved www.bitcoin.org
Oyedele, A. A., Ajayi, A. O., Oyedele, L. O., Bello, S. A., & Jimoh, K. O. (2023). Performance evaluation of deep learning and boosted trees for cryptocurrency closing price prediction. Expert Systems with Applications, 213. https://doi.org/10.1016/j.eswa.2022.119233
Parente, M., Rizzuti, L., & Trerotola, M. (2024). A profitable trading algorithm for cryptocurrencies using a Neural Network model. Expert Systems with Applications, 238. https://doi.org/10.1016/j.eswa.2023.121806
Ramadhan, Z. I., & Widiputra, H. (2024). Comparative analysis of recurrent neural network models performance in predicting Bitcoin prices. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 8(3), 377–388. https://doi.org/10.29207/resti.v8i3.5810
Ren, Y.-S., Ma, C.-Q., Kong, X.-L., Baltas, K., & Zureigat, Q. (2022). Past, present, and future of the application of machine learning in cryptocurrency research. Research in International Business and Finance, 63, 101799. https://doi.org/10.1016/j.ribaf.2022.101799
Rizkilloh, M. F., & Widiyanesti, S. (2022). Prediksi harga cryptocurrency menggunakan algoritma Long Short Term Memory (LSTM). Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 6(1), 25–31. https://doi.org/10.29207/resti.v6i1.3630
Singh, S., Pise, A., & Yoon, B. (2024). Prediction of Bitcoin stock price using feature subset optimization. Heliyon, 10(7), e28415. https://doi.org/10.1016/j.heliyon.2024.e28415
Uçkan, T. (2024). Integrating PCA with deep learning models for stock market Forecasting: An analysis of Turkish stocks markets. Journal of King Saud University - Computer and Information Sciences, 36(8). https://doi.org/10.1016/j.jksuci.2024.102162
Viéitez, A., Santos, M., & Naranjo, R. (2024). Machine learning Ethereum cryptocurrency prediction and knowledge-based investment strategies. Knowledge-Based Systems, 299. https://doi.org/10.1016/j.knosys.2024.112088
Yae, J., & Tian, G. Z. (2022). Out-of-sample forecasting of cryptocurrency returns: A comprehensive comparison of predictors and algorithms. Physica A: Statistical Mechanics and Its Applications, 598, 127379. https://doi.org/10.1016/j.physa.2022.127379
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ahsan Firdaus, Riza Adrianti Supono
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International (CC-BY-SA). that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
