Prediksi Arah Harga Cryptocurrency Menggunakan Hybrid Lstm Encoder dan Xgboost Head: Implementasi dan Evaluasi pada 10 Aset Digital Utama

Ade Kurniawan; Muliyono; Hari Suriadi

Authors

Ade Kurniawan Universitas Putra Indonesia "YPTK" Author
Muliyono Universitas Muhammadiyah Sumatera Barat Author
Hari Suriadi Universitas Muhammadiyah Sumatera Barat Author

Keywords:

Cryptocurrency, Price Prediction, Hybrid Model, LSTM, XGBoost, Algorithmic Trading

Abstract

The primary challenge in cryptocurrency price prediction lies in the market’s highly volatile, non-linear, and near–random walk behavior, which makes traditional predictive models unable to achieve consistent accuracy. This study aims to develop and evaluate a hybrid model combining Long Short-Term Memory (LSTM) and XGBoost to predict price direction and returns for ten major cryptocurrencies using daily data from 2023 to 2025. Historical data were processed through feature engineering, normalization, and sliding-window sequence construction, and the models were evaluated using TimeSeriesSplit to prevent data leakage. The results show that the hybrid model consistently outperformed both LSTM and XGBoost, achieving an average directional accuracy of 58.6%, significantly higher than the baselines (51.7% for LSTM and 53.6% for XGBoost). The average RMSE of 0.0289 indicates stable return predictions without systematic bias. Statistical validation through paired t-tests and McNemar tests confirmed the significance of the improvement at p < 0.001. A trading simulation using a 1-day holding period produced an annualized return of 41.5% with a Sharpe ratio of 1.12, outperforming the buy-and-hold strategy. These findings highlight that integrating LSTM’s temporal representation with XGBoost’s non-linear learning capabilities is an effective and computationally efficient approach for cryptocurrency price forecasting, offering practical value for the development of algorithmic trading systems.

References

Atsalakis, G. S., & Valavanis, K. P. (2009). Surveying stock market forecasting techniques – Part II: Soft computing methods. Expert Systems with Applications, 36(3), 5932–5941.

Bergmeir, C., Hyndman, R. J., & Koo, B. (2018). A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics & Data Analysis, 120, 70–83.

Bollinger, J. (2002). Bollinger on Bollinger Bands. McGraw-Hill.

Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794).

Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 785–794.

Chollet, F. (2018). Deep Learning with Python. Manning.

Corbet, S., Larkin, C., & Lucey, B. (2019). The contagion effects of the COVID-19 pandemic on the cryptocurrency market. Finance Research Letters, 35, 101–110.

Corbet, S., Meegan, A., Larsen, C., Lucey, B., & Yarovaya, L. (2018). Exploring the dynamic relationships between cryptocurrencies and other financial assets. Economics Letters, 165, 28–34.

Dantas, T. M., Oliveira, F. L. C., & Reiff, M. (2022). Hybrid neural networks ensemble for financial time series forecasting. Neurocomputing, 498, 86–99.

De Prado, M. L. (2018). Advances in Financial Machine Learning. Wiley.

Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669.

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.

Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.

Kim, J., & Kang, S. (2020). Financial time series forecasting using LSTM and XGBoost. IEEE Access, 8, 189215–189228.

Kuncheva, L. I. (2014). Combining Pattern Classifiers: Methods and Algorithms (2nd ed.). John Wiley & Sons.

Kyle, A. S. (1985). Continuous auctions and insider trading. Econometrica, 53(6), 1315–1335.

Nadarajah, S., & Chu, J. (2017). On the inefficiency of Bitcoin. Economics Letters, 150, 6–9.

Permentier, E., Mahroji, M., & Setiawan, H. (2024). Optimasi prediksi harga cryptocurrency berbasis model machine learning. Journal Teknik Informatika ITB, 12(3), 215–234.

Silvanus, A., Wijaya, B., & Karjono. (2022). Bitcoin price forecasting using seasonal log-differenced XGBoost and LSTM hybrid model. Sistemasi: Jurnal Sistem Informasi, 11(3), 512–528.

Wang, J., Wang, J., & Zhang, Z. (2020). Stock price prediction using LSTM. Neural Computing and Applications, 32(17), 13029–13038.

Wilder, J. W. (1978). New Concepts in Technical Trading Systems. Trend Research.

Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2), 241–259.

Zhang, W., Li, Y., Gao, Q., & Zhou, Y. (2023). Deep learning based ensemble model for cryptocurrency price prediction. Neural Networks, 159, 90–101.

Zhou, Z. H. (2012). Ensemble Methods: Foundations and Algorithms. CRC Press.

Lo, A. W. (2004). The adaptive markets hypothesis. The Journal of Portfolio Management, 30(5), 15–29.

Urquhart, A. (2016). The inefficiency of Bitcoin. Economics Letters, 148, 80–82.

Zhang, X., Li, Y., & Wang, J. (2023). Transformer-based models for cryptocurrency forecasting. IEEE Transactions on Neural Networks and Learning Systems, 34(4), 1542–1556.