LSTM Sinir Ağı ve ARIMA Zaman Serisi Modelleri Kullanılarak Bitcoin Fiyatının Tahminlenmesi ve Yöntemlerin Karşılaştırılması

Öz

Finansal varlıkların gelecekteki değerlerinin tahmini yatırımcılar için varlıklarını korumak adına önemlidir. 2008 yılında hayatımıza giren ve finansal varlıklar konusunda radikal bir değişiklik olan Bitcoin ise eski ve yeni yatırımcıların ilgisini çekmiş durumdadır. Ancak Bitcoin, doğası gereği diğer finansal varlıklara göre değerini belirleyen farklı parametreler içermektedir ve geleneksel tahmin yöntemleri Bitcoin gibi çok hareketli değerlere sahip finansal varlıkları tahmin etmekte güçlük çekmektedir. Bu çalışmada çok değişkenli LSTM sinir ağı ve klasik ARIMA zaman serisi modeli kullanılarak Bitcoin’in gelecek değerinin tahmini için modeller geliştirilmiştir. Uygulanan iki modelin tahmin doğruluğu performans değerlendirme metrikleri olan hata metrikleri kullanılarak karşılaştırılmıştır. Deneysel çalışmalar sonucu, LSTM sinir ağı modeli yakın ve uzak gelecek için düşük hata oranı ile tahmin performansı gerçekleştirirken ARIMA zaman serisi modeli yakın gelecek tahmini için düşük hata oranı ile tahmin performansı gerçekleştirmiştir.

Anahtar Kelimeler

• Zaman Serisi Tahmini
• Makine Öğrenmesi
• Bitcoin

Forecasting of Bitcoin Price Using LSTM Neural Network and ARIMA Time Series Models and Comparision of Methods

Abstract

It is important to forecast the future value of financial assets for investors to protect their assets. Bitcoin, which introduced to our lives in 2008 and is a radical change in financial assets, has been attracted the attention of both old and new investors. However, by its nature, Bitcoin contains different parameters that determine its value compared to other financial assets, and traditional forecasting methods have difficulty in predicting future values with very volatile financial assets such as Bitcoin. In this study, multivariate LSTM neural network and classic ARIMA time series model to forecast the future value of Bitcoin have been developed. The prediction accuracy of the two models applied has been compared using error metrics, which are performance evaluation metrics. As a result of the experimental studies, the LSTM neural network model has been performed prediction performance with a low error rate for the near and far future, while the ARIMA time series model has been performed prediction performance with a low error rate for the near future prediction.

Keywords

• Time Series Forecasting
• Machine Learning
• Bitcoin

Kaynakça

1. Nakamoto, S. (2008). Bitcoin: A peer-to-peer electronic cash system. Decentralized Business Review, 21260.
2. Hong, K. (2017). Bitcoin as an alternative investment vehicle. Information Technology and Management, 18(4), 265-275.
3. Huang, J. Z., Huang, W., & Ni, J. (2019). Predicting Bitcoin returns using high-dimensional technical indicators. The Journal of Finance and Data Science, 5(3), 140-155.
4. Chollet, F., & others. (2015). Keras. GitHub. Retrieved from https://github.com/fchollet/keras
5. Siami-Namini, S., & Namin, A. S. (2018). Forecasting economics and financial time series: ARIMA vs. LSTM. arXiv preprint arXiv:1803.06386.
6. Yunpeng, L., Di, H., Junpeng, B., & Yong, Q. (2017, November). Multi-step ahead time series forecasting for different data patterns based on LSTM recurrent neural network. In 2017 14th web information systems and applications conference (WISA) (pp. 305-310). IEEE.
7. Velankar, S., Valecha, S., & Maji, S. (2018, February). Bitcoin price prediction using machine learning. In 2018 20th International Conference on Advanced Communication Technology (ICACT) (pp. 144-147). IEEE.
8. McNally, S., Roche, J., & Caton, S. (2018, March). Predicting the price of bitcoin using machine learning. In 2018 26th euromicro international conference on parallel, distributed and network-based processing (PDP) (pp. 339-343). IEEE.

9. Azari, A. (2019). Bitcoin price prediction: An ARIMA approach. arXiv preprint arXiv:1904.05315.
10. Chen, Z., Li, C., & Sun, W. (2020). Bitcoin price prediction using machine learning: An approach to sample dimension engineering. Journal of Computational and Applied Mathematics, 365, 112395.
11. Kaggle, Machine Learning and Data Science Community, https://www.kaggle.com/
12. Wilder, J. W. (1978). New concepts in technical trading systems. Trend Research.
13. Selvin, S., Vinayakumar, R., Gopalakrishnan, E. A., Menon, V. K., & Soman, K. P. (2017, September). Stock price prediction using LSTM, RNN and CNN-sliding window model. In 2017 international conference on advances in computing, communications and informatics (icacci) (pp. 1643-1647). IEEE.
14. Graves, A. (2013). Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850.
15. Karevan, Z., & Suykens, J. A. (2020). Transductive LSTM for time-series prediction: An application to weather forecasting. Neural Networks, 125, 1-9.
16. Box, G. E., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: forecasting and control. John Wiley & Sons.