Research Article
BibTex RIS Cite

Günlük Bitcoin Değerini Tahmin Etmek İçin İstatistiksel ve Makine Öğrenimi Algoritmalarının Karşılaştırılması

Year 2021, Issue: 21, 444 - 454, 31.01.2021
https://doi.org/10.31590/ejosat.822153

Abstract

Finans dünyasında kripto para birimlerinin artan fiyat dalgalanmaları ve büyük kar potansiyeline sahip olması, özellikle Bitcoin olmak üzere bu para birimlerinin son derece doğrusal olmayan fiyatlarının sağlam tahminini yapmak için gelişmiş makine öğrenme teknolojilerinin kullanılması son yıllarda oldukça popular hale geldi. Ayrıca, gelecekteki değerini tahmin etmek, bilgisayar bilimi ve finans gibi farklı alanlarda ilgi çekici bir araştırma konusu haline geldi. Bu çalışmada, Bitcoin kripto para birimi fiyatını tahmin etmek için çeşitli istatistiksel ve makine öğrenme teknikleri uygulandı ve sonuçlar karşılaştırıldı. 1 Ocak 2013 ile 15 Ekim 2020 tarihleri arasında günlük Bitcoin verilerini kullanarak, istatistiksel teknikler arasında Hareketli Ortalama Analizi ve Otoregresif Entegre Hareketli Ortalama uygulanmış olup Makine Öğrenimi (ML) teknikleri arasında Sinir ağı, Derin sinir ağı, Tekrarlayan Sinir Ağı (RNN) ve en çok tercih edilen RNN'lerden biri olan LSTM, 32 pencere boyutu ile tek değişkenli zaman serisi analizi kapsamında uygulandı.
Sadece istatistiksel teknikleri uygulamak yerine makine öğrenimi algoritmalarının bu tarz tahminleme problemlerinde uygulanabilirliğini ve hatta daha iyi sonuçlar verdiği gösterildi ve 2021'in ilk ayının Bitcoin değerleri, oluşturulan sinir ağı ile tahmin edildi. Makine öğrenimi algoritmalarının yararlılığını kanıtlamak ve daha derin algoritmanın daha iyi sonuç verdiğini göstermek için, ortalama hata karesi (MSE), ortalama mutlak hata (MAE) ve ortalama mutlak yüzde hata (MAPE) ölçümleri kullanıldı. Sonuçların, derin öğrenme algoritmasının, algoritmaların derinliği ile orantılı olarak MSE, MAE ve MAPE ölçümleri açısından günlük Bitcoin fiyatını tahmin etmede diğer yöntemlere göre daha iyi sonuç verdiği ortaya konulmuştur. Ancak, bu çalışmada seçilen parametrelere göre LSTM, ağı eğitilememiş olup, ARIMA istatistiksel yöntemi ve diğer ML algoritmalarından daha iyi sonuçlar elde edilemedi.

References

  • Nakamoto, S. (2008). Bitcoin whitepaper. URL: https://bitcoin. org/bitcoin. pdf-(Дата обращения: 17.07. 2019).
  • Higbee, A. (2018). The role of crypto-currency in cybercrime. Computer Fraud & Security, 2018(7), 13-15.
  • Zhang, Y. Q., & Wan, X. (2007). Statistical fuzzy interval neural networks for currency exchange rate time series prediction. Applied Soft Computing, 7(4), 1149-1156.
  • Jalles, J. T. (2009). Structural time series models and the Kalman Filter: a concise review.
  • Refenes, A. N., Zapranis, A., & Francis, G. (1994). Stock performance modeling using neural networks: a comparative study with regression models. Neural networks, 7(2), 375-388.
  • Yao, J., & Tan, C. L. (2000). A case study on using neural networks to perform technical forecasting of forex. Neurocomputing, 34(1-4), 79-98.
  • Tsai, Y. T., Zeng, Y. R., & Chang, Y. S. (2018, August). Air pollution forecasting using RNN with LSTM. In 2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech) (pp. 1074-1079). IEEE.
  • Albariqi, R., & Winarko, E. (2020, February). Prediction of Bitcoin Price Change using Neural Networks. In 2020 International Conference on Smart Technology and Applications (ICoSTA) (pp. 1-4). IEEE.
  • Bakar, N. A., & Rosbi, S. (2017). Autoregressive integrated moving average (ARIMA) model for forecasting cryptocurrency exchange rate in high volatility environment: A new insight of bitcoin transaction. International Journal of Advanced Engineering Research and Science, 4(11), 237311.
  • Ayaz, Z., Fiaidhi, J., Sabah, A., & Anwer Ansari, M. (2020). Bitcoin Price Prediction using ARIMA Model.
  • Azari, A. (2019). Bitcoin price prediction: An ARIMA approach. arXiv preprint arXiv:1904.05315.
  • Alahmari, S. A. (2019). Using Machine Learning ARIMA to Predict the Price of Cryptocurrencies. ISeCure-The ISC International Journal of Information Security, 11(3), 139-144.
  • Munim, Z. H., Shakil, M. H., & Alon, I. (2019). Next-day bitcoin price forecast. Journal of Risk and Financial Management, 12(2), 103.

Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns

Year 2021, Issue: 21, 444 - 454, 31.01.2021
https://doi.org/10.31590/ejosat.822153

Abstract

Increasing fluctuations in pricing and having great potential for profit in finance world, utilization in advanced machine learning technologies to make robust prediction of highly nonlinear prices of cryptocurrencies especially Bitcoin have attracted great attention in recent years and forecasting its value have become an interesting research subject in different areas such as computer science and finance. In this study, various statistical and machine learning techniques have been conducted and compared to predict Bitcoin crypto currency price. By using the historical daily Bitcoin data between January 1, 2013 to October 15, 2020, Moving Average Analysis and Autoregressive Integrated Moving Average among the statistical techniques, and among Machine Learning (ML) techniques Neural network, Deep neural network, Recurrent Neural Network (RNN) and LSTM, one of the most preferred RNN have been applied for the univariate time series analysis with window size of 32. It has aimed to justify the usefulness of the machine learning algorithms instead of just apply statistical techniques. Besides, Bitcoin value of the first month of the 2021 has been predicted. To prove the usefulness of ML algorithms, and to show that deeper algorithm results better, mean squared error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) metrics have been used for comparison. The results have revealed that deep learning algorithm yields better than other methods in predicting daily Bitcoin price in terms of MSE, MAE and MAPE metrics proportional to the deepness of the algorithms. Nonetheless, LSTM does not have capability to train the network according to the parameters selected during this study and it has not been outperformed than ARIMA statistical method and other ML algorithms.

References

  • Nakamoto, S. (2008). Bitcoin whitepaper. URL: https://bitcoin. org/bitcoin. pdf-(Дата обращения: 17.07. 2019).
  • Higbee, A. (2018). The role of crypto-currency in cybercrime. Computer Fraud & Security, 2018(7), 13-15.
  • Zhang, Y. Q., & Wan, X. (2007). Statistical fuzzy interval neural networks for currency exchange rate time series prediction. Applied Soft Computing, 7(4), 1149-1156.
  • Jalles, J. T. (2009). Structural time series models and the Kalman Filter: a concise review.
  • Refenes, A. N., Zapranis, A., & Francis, G. (1994). Stock performance modeling using neural networks: a comparative study with regression models. Neural networks, 7(2), 375-388.
  • Yao, J., & Tan, C. L. (2000). A case study on using neural networks to perform technical forecasting of forex. Neurocomputing, 34(1-4), 79-98.
  • Tsai, Y. T., Zeng, Y. R., & Chang, Y. S. (2018, August). Air pollution forecasting using RNN with LSTM. In 2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech) (pp. 1074-1079). IEEE.
  • Albariqi, R., & Winarko, E. (2020, February). Prediction of Bitcoin Price Change using Neural Networks. In 2020 International Conference on Smart Technology and Applications (ICoSTA) (pp. 1-4). IEEE.
  • Bakar, N. A., & Rosbi, S. (2017). Autoregressive integrated moving average (ARIMA) model for forecasting cryptocurrency exchange rate in high volatility environment: A new insight of bitcoin transaction. International Journal of Advanced Engineering Research and Science, 4(11), 237311.
  • Ayaz, Z., Fiaidhi, J., Sabah, A., & Anwer Ansari, M. (2020). Bitcoin Price Prediction using ARIMA Model.
  • Azari, A. (2019). Bitcoin price prediction: An ARIMA approach. arXiv preprint arXiv:1904.05315.
  • Alahmari, S. A. (2019). Using Machine Learning ARIMA to Predict the Price of Cryptocurrencies. ISeCure-The ISC International Journal of Information Security, 11(3), 139-144.
  • Munim, Z. H., Shakil, M. H., & Alon, I. (2019). Next-day bitcoin price forecast. Journal of Risk and Financial Management, 12(2), 103.
There are 13 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Articles
Authors

Betul Aygun 0000-0001-9610-9235

Eylul Kabakcı Gunay 0000-0001-5547-4316

Publication Date January 31, 2021
Published in Issue Year 2021 Issue: 21

Cite

APA Aygun, B., & Kabakcı Gunay, E. (2021). Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns. Avrupa Bilim Ve Teknoloji Dergisi(21), 444-454. https://doi.org/10.31590/ejosat.822153