Bitcoin Price Forecasting using Seasonal Log-Differenced XGBoost with 2014–2025 Data

Muhammmad Akbar

Abstract


Bitcoin, as a decentralized digital currency, experiences significant price fluctuations, making accurate price forecasting a complex yet valuable challenge. Price forecasting is essential in economic decision-making, serving as the foundation for portfolio construction, risk analysis, and investment strategy development. Bitcoin's high volatility makes it an attractive asset for investors but also poses significant risks, necessitating sophisticated forecasting tools and models to mitigate uncertainty. The XGBoost model in regression is widely known and effectively applied to handle time series data. This model can capture complex nonlinear relationships in Bitcoin price data, providing more accurate forecasts than traditional statistical models. The research methodology includes data collection, data preprocessing, stationarity checking, differencing, feature engineering, data division into training and testing sets, XGBoost model training, prediction and evaluation, and result visualization. The research results show that the XGBoost model achieves a Mean Absolute Error of 8.26% and an RMSE of 9.87%, indicating excellent forecasting accuracy. The implications of this research could potentially assist investors and traders in improving their strategies and risk management.

Keywords


Forecasting; Bitcoin; XGBoost Model; MAE; Digital Currency

Full Text:

PDF

References


Q. Guo, S. Lei, Q. Ye, and Z. Fang, “MRC-LSTM: A Hybrid Approach of Multi-scale Residual CNN and LSTM to Predict Bitcoin Price,” 2022 International Joint Conference on Neural Networks (IJCNN), p. 1, Jul. 2021, DOI: 10.1109/ijcnn52387.2021.9534453.

M. Iqbal, M. H. Iqbal, F. H. Jaskani, K. Iqbal, and A. Hassan, “Time-Series Prediction of Cryptocurrency Market using Machine Learning Techniques,” EAI Endorsed Transactions on Creative Technologies, Vol. 8, No. 28, p. 170286, Jul. 2021, DOI: 10.4108/eai.7-7-2021.170286.

A. Bouteska, M. Z. Abedin, P. Hájek, and K. Yuan, “Cryptocurrency Price Forecasting – A Comparative Analysis of Ensemble Learning and Deep Learning Methods,” International Review of Financial Analysis, Vol. 92, p. 103055, Dec. 2023, DOI: 10.1016/j.irfa.2023.103055.

H. S. Jung, J. H. Kim, and H. Lee, “Decoding Bitcoin: Leveraging Macro-and Micro-Factors in Time Series Analysis for Price Prediction,” PeerJ Computer Science, Vol. 10, Sep. 2024, DOI: 10.7717/peerj-cs.2314.

S. Rikli, D. N. Bigler, M. Pfenninger, and J. Osterrieder, “Wasserstein GAN: Deep Generation Applied on Bitcoins Financial Time Series,” arXiv (Cornell University), Jan. 2021, DOI: 10.48550/arxiv.2107.06008.

A. L. Putra and A. Kurniawati, “Analisis Prediksi Harga Saham PT. Astra International Tbk menggunakan Metode Autoregressive Integrated Moving Average (ARIMA) dan Support Vector Regression (SVR),” Jurnal Ilmiah Komputasi, Vol. 20, No. 3, Sep. 2021, DOI: 10.32409/jikstik.20.3.2732.

G. Cohen and A. Aiche, “Predicting the Bitcoin’s Price using AI,” Frontiers in Artificial Intelligence, Vol. 8, Apr. 2025, DOI: 10.3389/frai.2025.1519805.

D. R. Chandranegara, R. A. Afif, C. S. K. Aditya, W. Suharso, and H. Wibowo, “Prediksi Harga Saham Jakarta Islamic Index menggunakan Metode Long Short-Term Memory,” Jurnal Edukasi dan Penelitian Informatika (JEPIN), Vol. 9, No. 1, p. 129, Apr. 2023, DOI: 10.26418/jp.v9i1.57561.

S. Sudaryono, Q. Aini, N. Lutfiani, F. Hanafi, and U. Rahardja, “Application of Blockchain Technology for iLearning Student Assessment,” IJCCS (Indonesian Journal of Computing and Cybernetics Systems), Vol. 14, No. 2, p. 209, Apr. 2020, DOI: 10.22146/ijccs.53109.

Muntafiah, S. Bakri, and A. Rais, “Tinjauan Transaksi Crypto Currency berbasis Keabsahan Kontemporer Syariah” Academica Journal of Multidisciplinary Studies, Vol. 6, No. 2, p. 335, Dec. 2022, DOI: 10.22515/academica.v6i2.5931.

R. Böhme, N. Christin, B. Edelman, and T. Moore, “Bitcoin: Economics, Technology, and Governance,” The Journal of Economic Perspectives, Vol. 29, No. 2, p. 213, Apr. 2015, DOI: 10.1257/jep.29.2.213.

D. Shah, D. Patel, J. Adesara, P. Hingu, and M. Shah, “Integrating Machine Learning and Blockchain to Develop a System to Veto the Forgeries and Provide Efficient Results in Education Sector,” Visual Computing for Industry Biomedicine and Art, Vol. 4, No. 1, Jun. 2021, DOI: 10.1186/s42492-021-00084-y.

S. Laksono and W. Candra, “Artificial Intelligence dan Kardiologi: A Mini Review,” Health & Medical Journal, Vol. 4, No. 2. p. 130, May 01, 2022. DOI: 10.33854/heme.v4i2.964.

R. Lou, Z. Lv, S. Dang, T. Su, and X. Li, “Application of Machine Learning in Ocean Data,” Multimedia Systems, Vol. 29, No. 3, p. 1815, Feb. 2021, DOI: 10.1007/s00530-020-00733-x.

J. M. Ahn, J. Kim, and K. Kim, “Ensemble Machine Learning of Gradient Boosting (XGBoost, LightGBM, CatBoost) and Attention-based CNN-LSTM for Harmful Algal Blooms Forecasting,” Toxins, Vol. 15, No. 10, p. 608, Oct. 2023, DOI: 10.3390/toxins15100608.

A. Ferrario and R. Hämmerli, “On Boosting: Theory and Applications,” SSRN Electronic Journal, Jan. 2019, DOI: 10.2139/ssrn.3402687.

T. Chen and C. Guestrin, “XGBoost,” p. 785, Aug. 2016, DOI: 10.1145/2939672.2939785.

J. Ma, Z. Yu, Y. Qu, J. Xu, and Y. Cao, “Application of the XGBoost Machine Learning Method in PM2.5 Prediction: A Case Study of Shanghai,” Aerosol and Air Quality Research, Vol. 20, No. 1, p. 128, Dec. 2019, DOI: 10.4209/aaqr.2019.08.0408.

P. Hu et al., “A Comparison of LASSO Regression and Tree-based Models for Delayed Cerebral Ischemia in Elderly Patients with Subarachnoid Hemorrhage,” Frontiers in Neurology, Vol. 13, Mar. 2022, DOI: 10.3389/fneur.2022.791547.

A. Anghel, N. Papandreou, T. Parnell, A. D. Palma, and H. Pozidis, “Benchmarking and Optimization of Gradient Boosted Decision Tree Algorithms,” arXiv (Cornell University), Sep. 2018, Accessed: Feb. 2025. [Online]. Available: https://arxiv.org/pdf/1809.04559.pdf

Y. Kang, M. Özdoğan, X. Zhu, Z. Ye, C. Hain, and M. C. Anderson, “Comparative Assessment of Environmental Variables and Machine Learning Algorithms for Maize Yield Prediction in the US Midwest,” Environmental Research Letters, Vol. 15, No. 6, p. 64005, Mar. 2020, DOI: 10.1088/1748-9326/ab7df9.

R. Holla, “Advanced Feature Engineering for Time Series Data.” Jun. 2024. Accessed: Jul. 14, 2025. [Online]. Available: https://medium.com/@rahulholla1/advanced-feature-engineering-for-time-series-data-5f00e3a8ad29

J. Heaton, “An Empirical Analysis of Feature Engineering for Predictive Modeling,” SoutheastCon, p. 1, Mar. 2016, DOI: 10.1109/secon.2016.7506650.

R. Adawiyah, M. Muljono, and W. E. Nugroho, “Algoritma Naive Bayes untuk memprediksi Bimbingan Konseling Siswa Sekolah Menengah Kejuruan,” Smart Comp Jurnalnya Orang Pintar Komputer, Vol. 12, No. 3, p. 723, Jul. 2023, DOI: 10.30591/smartcomp.v12i3.5365.

D. A. Wibisono, D. Anggraeni, and A. F. Hadi, “Perbaikan Model Seasonal ARIMA dengan Metode Ensemble Kalman Filter pada Hasil Prediksi Curah Hujan” Majalah Ilmiah Matematika dan Statistika, Vol. 19, No. 1, p. 9, Mar. 2019, DOI: 10.19184/mims.v19i1.17262.

V. Naghashi, M. Boukadoum, and A. B. Diallo, “A Multiscale Model for Multivariate Time Series Forecasting,” Scientific Reports, Vol. 15, No. 1, Jan. 2025, DOI: 10.1038/s41598-024-82417-4.

V. M. Manikandan and S. Neethirajan, “Decoding Poultry Welfare from Sound—A Machine Learning Framework for Non-Invasive Acoustic Monitoring,” Sensors, Vol. 25, No. 9, p. 2912, May 2025, DOI: 10.3390/s25092912.

U. M. Rifanti, H. Pujiharsono, A. W. Setiawan, and J. Hendry, “Implementasi Moving Average Filter untuk Koreksi Kesalahan Sensor Pengukur Kedalaman Air,” ELKOMIKA Jurnal Teknik Energi Elektrik Teknik Telekomunikasi & Teknik Elektronika, Vol. 8, No. 2, p. 432, May 2020, DOI: 10.26760/elkomika.v8i2.432.

S. O. Odhiambo, N. O. Cornelious, and H. Waititu, “Developing a Hybrid ARIMA-XGBOOST Model for Analysing Mobile Money Transaction Data in Kenya,” Asian Journal of Probability and Statistics, Vol. 26, No. 10, p. 108, Oct. 2024, DOI: 10.9734/ajpas/2024/v26i10662.

R. K. Klimberg and S. J. Ratick, “Development of a Practical and Effective Forecasting Performance Measure,” in Advances in business and management forecasting, Emerald Publishing Limited, 2017, p. 103. DOI: 10.1108/s1477-407020170000012007.

F. Rodrigues and M. P. Machado, “High-Frequency Cryptocurrency Price Forecasting using Machine Learning Models: A Comparative Study,” Mar. 2025, DOI: 10.20944/preprints202503.0261.v1.

F. Annasiyah and M. Prastuti, “Peramalan Konsumsi Energi Listrik untuk Sektor Industri di PT PLN (Persero) Area Gresik menggunakan Metode Time Series Regression dan ARIMA,” Jurnal Sains dan Seni ITS, Vol. 12, No. 1, May 2023, DOI: 10.12962/j23373520.v12i1.104264.

C. S. Kalengkongan, Y. Langi, and N. Nainggolan, “Analisis Volatilitas Harga Bawang Putih di Kota Manado menggunakan Model GARCH,” d Cartesian, Vol. 9, No. 1, p. 43, Jan. 2020, DOI: 10.35799/dc.9.1.2020.27398.

Z. Hossain, A. Rahman, Md. M. Hossain, and J. H. Karami, “Over-Differencing and Forecasting with Non-Stationary Time Series Data,” Dhaka University Journal of Science, Vol. 67, No. 1, p. 21, Jan. 2019, DOI: 10.3329/dujs.v67i1.54568.

M. Z. Rusminto, S. A. Wibowo, and F. S. Wahyuni, “Peramalan Harga Saham menggunakan Metode ARIMA (Autoregressive Integrated Moving Average) Time Series”, Jurnal Mahasiswa Teknik Informatika, Vol. 8, No. 2, p. 1263, Mar. 2024, DOI: 10.36040/jati.v8i2.9089.

D. Pratiwi, S. M. U. Agustini, W. Windasari, and E. N. Kencana, “Forecasting Farmer Exchange Rate in Bali Province using Seasonal Autoregressive Integrated Moving Average (SARIMA) Method,” Journal of Physics Conference Series, Vol. 1503, No. 1, p. 12002, Jul. 2020, DOI: 10.1088/1742-6596/1503/1/012002.

Y. A. Sir and A. H. H. Soepranoto, “Pendekatan Resampling Data untuk menangani Masalah Ketidakseimbangan Kelas,” Jurnal Komputer dan Informatika, Vol. 10, No. 1, p. 31, Mar. 2022, DOI: 10.35508/jicon.v10i1.6554.

D. Hediyati and I. M. Suartana, “Penerapan Principal Component Analysis (PCA) untuk Reduksi Dimensi pada Proses Clustering Data Produksi Pertanian di Kabupaten Bojonegoro,” Journal of Information Engineering and Educational Technology, Vol. 5, No. 2, p. 49, Dec. 2021, DOI: 10.26740/jieet.v5n2.p49-54.

P. K. Handayani, “Penerapan Principal Component Analysis untuk Peningkatan Kinerja Algoritma Decision Tree pada Iris Dataset,” Indonesian Journal of Technology Informatics and Science (IJTIS), Vol. 1, No. 2, p. 55, Jun. 2020, DOI: 10.24176/ijtis.v1i2.4939.

W. Astuti and A. Adiwijaya, “Principal Component Analysis sebagai Ekstraksi Fitur Data Microarray untuk Deteksi Kanker berbasis Linear Discriminant Analysis,” Jurnal Media Informatika Budidarma, Vol. 3, No. 2, p. 72, Apr. 2019, DOI: 10.30865/mib.v3i2.1161.

C. Li, “Preprocessing Methods and Pipelines of Data Mining: An Overview,” arXiv (Cornell University), Jan. 2019, DOI: 10.48550/arxiv.1906.08510.

D. anon and R. Ślepaczuk, “Hybrid Models for Financial Forecasting: Combining Econometric, Machine Learning, and Deep Learning Models,” Jan. 2025, DOI: 10.2139/ssrn.5268691.

R. Paita, N. Nainggolan, and Y. Langi, “Model Space Time Autoregressive (STAR) Orde 1 dan Penerapannya pada Prediksi Harga Beras di Kota Manado, Tomohon dan Kabupaten Minahasa Utara,” d CARTESIAN, Vol. 3, No. 1, p. 17, Feb. 2014, DOI: 10.35799/dc.3.1.2014.3798.

M. I. Naufal and C. Susetyo, “Prediksi Perubahan Penutupan Lahan Pasca Beroperasinya Gerbang Tol (Interchange) Pandaan di Kecamatan Pandaan Kabupaten Pasuruan menggunakan Metode Regresi Logistik Biner,” Jurnal Teknik ITS, Vol. 9, No. 1, Aug. 2020, DOI: 10.12962/j23373539.v9i1.48278.




DOI: https://doi.org/10.32520/stmsi.v14i6.5547

Article Metrics

Abstract view : 5 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.