A Hybrid Data Science Framework for Forecasting Bitcoin Prices using Traditional and AI Models
DOI:
https://doi.org/10.30871/jaic.v9i5.10631Keywords:
Bitcoin, Data Science Framework, Artificial Intelligence, IntermodelAbstract
Bitcoin, a highly volatile and decentralized digital asset, presents considerable challenges for accurate price forecasting. This study proposes an applied data science framework that compares traditional statistical approaches with modern Artificial Intelligence (AI)-based models to predict Bitcoin’s daily closing price. Using BTC-USD historical data from January 2020 to December 2024, we converted prices into Indonesian Rupiah (IDR) to increase local relevance. Our forecasting horizon is 30 days, based on a 60-day lookback window. We evaluate six models: Linear Regression, ARIMA, and Prophet as traditional techniques, alongside Random Forest, XGBoost, and Long Short-Term Memory (LSTM) networks as AI approaches. All models were trained using lag-based or sequence-based time series features and evaluated using MAE, RMSE, R², MAPE, and SMAPE. Results show that AI models, particularly LSTM and XGBoost, offer better performance in capturing short-term non-linear dynamics compared to traditional models. LSTM provides high accuracy, though with greater computational demand, while XGBoost strikes a balance between speed and precision. Prophet and ARIMA remain effective for quick and interpretable forecasts but struggle with abrupt trend shift common in cryptocurrency markets. In addition to performance metrics, we include a robustness analysis based on median absolute error and outlier detection to assess model stability under extreme variations. Visual analytics—including forecast curves, error distributions, and uncertainty bounds—help interpret and communicate model behavior. This comprehensive evaluation offers practical insights for investors, analysts, and fintech practitioners, and the pipeline can be extended to other volatile assets.
Downloads
References
[1] T. Phaladisailoed and T. Numnonda, “Machine learning models comparison for bitcoin price prediction,” Proc. 2018 10th Int. Conf. Inf. Technol. Electr. Eng. Smart Technol. Better Soc. ICITEE 2018, no. January, pp. 506–511, 2018, doi: 10.1109/ICITEED.2018.8534911.
[2] S. Saraswathi, J. S. Sridhala, A. Elavazhagan, J. S. Sabharwal, and S. I. Mohammad, “An Ensemble Machine Learning Technique for Bitcoin Price Prediction,” J. Trends Comput. Sci. Smart Technol., vol. 6, no. 2, pp. 153–167, 2024, doi: 10.36548/jtcsst.2024.2.005.
[3] J. T. Kjellstadli, E. Bering, M. Hendrick, S. Pradhan, and A. Hansen, “Can local stress enhancement induce stability in fracture processes? Part I: Apparent stability,” Front. Phys., vol. 7, no. JULY, pp. 1–8, 2019, doi: 10.3389/fphy.2019.00098.
[4] R. Manivannan, S. Subashree, G. Venkateshwaran, G. Pushpa, E. Saranya, and M. Rajakumaran, “An Intelligent and Accurate Bitcoin Price Forecasting using ARIMA Model,” SSRN Electron. J., 2025, doi: 10.2139/ssrn.5091288.
[5] I. Suryani and H. Harafani, “Predicting the Bitcoin Price Using Linear Regression Optimized With Exponential Smoothing,” J. Ris. Inform., vol. 3, no. 3, pp. 277–282, 2021, doi: 10.34288/jri.v3i3.238.
[6] Suresh N, Priya B, Sai Teja M, Sai Krishna B, and Lakshmi G, “Historical analysis and forecasting of stock market using fbprophet,” South Asian J. Eng. Technol., vol. 12, no. 3, pp. 152–157, 2022, doi: 10.26524/sajet.2022.12.43.
[7] M. F. Arfa, M. R. AlFathan, H. B. Lumbantobing, and R. Rahmadenni, “Prediksi Harga Cryptocurrency Dengan Metode Linier Regresi,” SENTIMAS Semin. Nas. Penelit. dan Pengabdi. Masy., vol. 1, no. 1, pp. 8–15, 2023, [Online]. Available: https://journal.irpi.or.id/index.php/sentimas/article/view/609%0Ahttps://journal.irpi.or.id/index.php/sentimas/article/download/609/332
[8] C. Pebriyanti and G. M. Suranegara, “Evaluation of Scalability and Resilience of Hyperledger Fabric in Blockchain Implementation for Diploma Management,” vol. 9, no. 3, 2025.
[9] Y. Hua, “Bitcoin price prediction using ARIMA and LSTM,” E3S Web Conf., vol. 218, pp. 1–5, 2020, doi: 10.1051/e3sconf/202021801050.
[10] F. Orte, J. Mira, M. J. Sánchez, and P. Solana, “A random forest-based model for crypto asset forecasts in futures markets with out-of-sample prediction,” Res. Int. Bus. Financ., vol. 64, no. August 2022, 2023, doi: 10.1016/j.ribaf.2022.101829.
[11] S. A. Basher and P. Sadorsky, “Forecasting Bitcoin price direction with random forests: How important are interest rates, inflation, and market volatility?,” Mach. Learn. with Appl., vol. 9, no. June, p. 100355, 2022, doi: 10.1016/j.mlwa.2022.100355.
[12] Y. He, “Prediction of Bitcoin Daily Returns Based on OLS , XGBoost , and CNN Machine Learning Models,” no. Ecai 2024, pp. 181–187, 2025, doi: 10.5220/0013212400004568.
[13] A. Hafid, M. Ebrahim, M. Rahouti, and D. Oliveira, “Cryptocurrency Price Forecasting Using XGBoost Regressor and Technical Indicators,” Conf. Proc. IEEE Int. Performance, Comput. Commun. Conf., pp. 1–9, 2024, doi: 10.1109/IPCCC59868.2024.10850357.
[14] S. Zhang, M. Li, and C. Yan, “The Empirical Analysis of Bitcoin Price Prediction Based on Deep Learning Integration Method,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/1265837.
[15] A. R. Kamila, J. F. Andry, A. Wahyu, C. Kusuma, W. Prasetyo, and G. H. Derhass, “Analysis Comparison of K-Nearest Neighbor , Multi-Layer Perceptron , and Decision Tree Algorithms in Diamond Price Prediction,” COGITO Smart J., vol. 10, no. 2, pp. 298–311, 2024.
[16] Ferdiansyah, S. H. Othman, R. Zahilah Raja Md Radzi, D. Stiawan, Y. Sazaki, and U. Ependi, “A LSTM-Method for Bitcoin Price Prediction: A Case Study Yahoo Finance Stock Market,” ICECOS 2019 - 3rd Int. Conf. Electr. Eng. Comput. Sci. Proceeding, no. June, pp. 206–210, 2019, doi: 10.1109/ICECOS47637.2019.8984499.
[17] F. Ding, “The Research on the Prediction of Cryptocurrency Based on Linear Regression and LSTM,” pp. 1472–1481, 2023, doi: 10.2991/978-94-6463-102-9_154.
[18] Z. Ye, Y. Wu, H. Chen, Y. Pan, and Q. Jiang, “A Stacking Ensemble Deep Learning Model for Bitcoin Price Prediction Using Twitter Comments on Bitcoin,” Mathematics, vol. 10, no. 8, 2022, doi: 10.3390/math10081307.
[19] P. R. Panggabean and H. A. Aidilof, “Sentiment Analysis of Public Comments on X Social Media Related to Israeli Product Boycotts Using The Long Short-Term Memory ( LSTM ) Method,” vol. 9, no. 3, pp. 775–783, 2025.
[20] B. Hakim, “Analisa Sentimen Data Text Preprocessing Pada Data Mining Dengan Menggunakan Machine Learning,” JBASE - J. Bus. Audit Inf. Syst., vol. 4, no. 2, pp. 16–22, 2021, doi: 10.30813/jbase.v4i2.3000.
[21] Y. Yang, J. Xiong, L. Zhao, X. Wang, L. Hua, and L. Wu, “A Novel Method of Blockchain Cryptocurrency Price Prediction Using Fractional Grey Model,” Fractal Fract., vol. 7, no. 7, pp. 1–19, 2023, doi: 10.3390/fractalfract7070547.
[22] Sagaino, T. M. S. Mulyana, I. G. N. Suryantara, J. A. Ginting, and F. Adikara, “Pemetaan Kejadian Bencana Alam Di Jawa Barat Menggunakan Algoritma K-Means,” 2022.
[23] D. Mao and J. R. Edwards, Simulation of chemically-reacting gas-solid flowfields using a preconditioning strategy. 2003. doi: 10.2514/6.2003-4110.
[24] S. D. Amalia, M. A. Barata, and P. E. Yuwita, “Optimization of Random Forest Algorithm with Backward Elimination Method in Classification of Academic Stress Levels,” J. Appl. Informatics Comput., vol. 9, no. 3, pp. 633–641, 2025.
[25] P. Madhumathy, M. Vinoth Kumar, and R. Umamaheswari, Machine Learning and Iot for Intelligent Systems and Smart Applications. 2021. doi: 10.1201/9781003194415.
[26] P. Boozary, S. Sheykhan, and H. GhorbanTanhaei, “Forecasting the Bitcoin price using the various Machine Learning: A systematic review in data-driven marketing,” Syst. Soft Comput., vol. 7, no. February, p. 200209, 2025, doi: 10.1016/j.sasc.2025.200209.
[27] Y. Si, “Using ARIMA model to analyse and predict bitcoin price,” BCP Bus. Manag., vol. 34, pp. 1210–1216, 2022, doi: 10.54691/bcpbm.v34i.3161.
[28] J. Brasil et al., Advances in Data Science, vol. 11, no. 1. 2020. doi: 10.1002/9781119695110.
[29] Y. Lou, Advances in Data Science. 2020. doi: 10.1002/9781119695110.
[30] P. Overview et al., “• Data Science General • Business Science”.
[31] M. Clinton, T. Manullang, A. Z. Rakhman, H. Tantriawan, and A. Setiawan, “Comparative Analysis of CNN, Transformers, and Traditional ML for Classifying Online Gambling Spam Comments in Indonesian,” J. Appl. Informatics Comput., vol. 9, no. 3, pp. 592–602, 2025, [Online]. Available: https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9468
[32] A. Christopher and T. M. S. Mulyana, “Klasifikasi Tumbuhan Angiospermae Menggunakan Algoritma K-Nearest Neighbor Berdasarkan Pada Bentuk Daun,” JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 7, no. 4, pp. 1233–1243, 2022, doi: 10.29100/jipi.v7i4.3211.
[33] Z. Yuan, “Gold and Bitcoin Price Prediction based on KNN, XGBoost and LightGBM Model,” Highlights Sci. Eng. Technol., vol. 39, pp. 720–725, 2023, doi: 10.54097/hset.v39i.6635.
[34] D. C. A. Mallqui and R. A. S. Fernandes, “Predicting the Direction, Maximum, Minimum and Closing Prices of Daily Bitcoin Exchange Rate Using Machine Learning Techniques,” Appl. Soft Comput. J., 2018, doi: https://doi.org/10.1016/j.asoc.2018.11.038.
[35] D. M. Beazley, Python Warning and Disclaimer Bulk Sales. 2006. [Online]. Available: http://dlx.b-ok.org/genesis/79000/73027e552f3bfa7bf634a71bab0744b3/_as/[Beazley]_Python_Essential_Reference(b-ok.org).pdf
[36] D. Cielen, A. Meysman, and M. Ali, Introducing data science : big data, machine learning, and more, using Python tools. 2016.
[37] A. Dimitriadou and A. Gregoriou, “Predicting Bitcoin Prices Using Machine Learning,” Entropy, vol. 25, no. 5, pp. 1–10, 2023, doi: 10.3390/e25050777.
[38] W. Lu, J. Li, Y. Li, A. Sun, and J. Wang, “A CNN-LSTM-based model to forecast stock prices,” Complexity, vol. 2020, 2020, doi: 10.1155/2020/6622927.
[39] B. Johnston and I. Mathur, Applied Supervised Learning with Python. 2019.
[40] Y. Ding, Y. Zhu, J. Feng, P. Zhang, and Z. Cheng, “Interpretable spatio-temporal attention LSTM model for flood forecasting,” Neurocomputing, vol. 403, 2020, doi: 10.1016/j.neucom.2020.04.110.
[41] Z. Fang, Y. Wang, L. Peng, and H. Hong, “Integration of convolutional neural network and conventional machine learning classifiers for landslide susceptibility mapping,” Comput. Geosci., vol. 139, no. October 2019, p. 104470, 2020, doi: 10.1016/j.cageo.2020.104470.
[42] P. Hiskiawan, C.-C. Chen, and Z.-K. Ye, “Processing of electrical resistivity tomography data using convolutional neural network in ERT-NET architectures,” Arab. J. Geosci., vol. 16, no. 10, pp. 1–14, 2023, doi: 10.1007/s12517-023-11690-w.
[43] A. Botchkarev, “A new typology design of performance metrics to measure errors in machine learning regression algorithms,” Interdiscip. J. Information, Knowledge, Manag., vol. 14, no. January, pp. 45–76, 2019, doi: 10.28945/4184.
[44] M. Amos, “Perbandingan Algoritma Linear Regression, Neural Network, Deep Learning, Dan K-Nearest Neighbor (K-NN) Untuk Prediksi Harga Bitcoin,” JSI J. Sist. Inf., vol. 14, no. 1, pp. 2450–2464, 2022, doi: 10.18495/jsi.v14i1.16561.
[45] S. Nakagawa, P. C. D. Johnson, and H. Schielzeth, “The coefficient of determination R2 and intra-class correlation coefficient from generalized linear mixed-effects models revisited and expanded,” J. R. Soc. Interface, vol. 14, no. 134, 2017, doi: 10.1098/rsif.2017.0213.
[46] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., vol. 7, pp. 1–24, 2021, doi: 10.7717/PEERJ-CS.623.
[47] S. Das, M. Billah, and S. A. Mumu, “A Hybrid Approach for Predicting Bitcoin Price Using Bi-LSTM and Bi-RNN Based Neural Network,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 13113 LNCS, no. December 2024, pp. 223–233, 2021, doi: 10.1007/978-3-030-91608-4_23.
[48] S. Fakharchian, “Designing a forecasting assistant of the Bitcoin price based on deep learning using market sentiment analysis and multiple feature extraction,” Soft Comput., vol. 27, no. 24, pp. 18803–18827, 2023, doi: 10.1007/s00500-023-09028-5.
[49] S. Chan, J. Chu, S. Nadarajah, and J. Osterrieder, “A Statistical Analysis of Cryptocurrencies,” J. Risk Financ. Manag., vol. 10, no. 2, p. 12, 2017, doi: 10.3390/jrfm10020012.
[50] P. D. Modi, K. Arshi, P. J. Kunz, and A. M. Zoubir, “A Data-driven Deep Learning Approach for Bitcoin Price Forecasting,” Int. Conf. Digit. Signal Process. DSP, vol. 2023-June, pp. 8–11, 2023, doi: 10.1109/DSP58604.2023.10167930.
[51] N. G. S. Lakshmi, V. Ajaykumar, B. Ashish, K. Hemalatha, T. Manohar, and V. Sivashankerreddy, “Comparative Bitcoin Price Prediction Using Multiple Machine Learning Techniques,” in Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET 2024, Atlantis Press International BV, 2024, pp. 1248–1258. doi: 10.2991/978-94-6463-471-6_120.
[52] I. Letteri, “A Comparative Analysis of Statistical and Machine Learning Models for Outlier Detection in Bitcoin Limit Order Books,” in Outlier Detection in Bitcoin Limit Order Books, 2025. [Online]. Available: http://arxiv.org/abs/2507.14960
[53] Paul J. Deitel and Harvey Deitel, Intro to Python for Computer Science and Data Science. 2020.
[54] N. I. Boyko and O. A. Tkachyk, “Hierarchical clustering algorithm for dendrogram construction and cluster counting,” Informatics Math. methods Simul., vol. 13, no. 1–2, pp. 5–15, 2023, doi: 10.15276/imms.v13.no1-2.5.
[55] M. Forina, C. Armanino, and V. Raggio, “Clustering with dendrograms on interpretation variables,” Anal. Chim. Acta, vol. 454, no. 1, pp. 13–19, 2002, doi: 10.1016/S0003-2670(01)01517-3.
[56] N. S. S. Kiranmai Balijepalli and V. Thangaraj, “Prediction of cryptocurrency’s price using ensemble machine learning algorithms,” Eur. J. Manag. Bus. Econ., 2025, doi: 10.1108/EJMBE-08-2023-0244.
[57] Y. Z. D. Z. S. C. S. G. Y. Ma, “Single-Image Crowd Counting via Multi-Column Convolutional Neural Network,” CVPR Pap., vol. 2, no. 35, pp. 589–597, 2016, doi: 10.1002/slct.201701956.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Puguh Hiskiawan, Jovan William, Louis Feliepe Tio Jansel
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 License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) 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 (See The Effect of Open Access).
