Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns
Yıl: 2021 Cilt: 0 Sayı: 21 Sayfa Aralığı: 444 - 454 Metin Dili: İngilizce DOI: 10.31590/ejosat.822153 İndeks Tarihi: 25-05-2023
Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns
Öz: Increasing fluctuations in pricing and having great profit potential, utilization in advanced machine learning technologies to make robust predictions of cryptocurrencies especially bitcoin have attracted great attention in recent years. In this study, various statistical techniques; Moving Average Analysis and Autoregressive Integrated Moving Average and machine learning (ML) techniques; Artificial Neural Network, Recurrent Neural Network (RNN) and Convolutional Neural Network have been conducted and compared to predict the future value of Bitcoin cryptocurrency price. They have been applied for the univariate time series analysis with a window size of 32. To prove the usefulness of ML algorithms, and to show that the results of RNN is a better, mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) indicators have been applied. The study revealed that recurrent neural network yields better results than other methods in predicting daily Bitcoin price in terms of MSE, MAE and MAPE metrics. Besides, Wilcoxon-Mann-Whitney nonparametric statistic test is applied to test the performance between ARIMA and machine learning algorithms.
Anahtar Kelime: Günlük Bitcoin Değerini Tahmin Etmek İçin İstatistiksel ve Makine Öğrenimi Algoritmalarının Karşılaştırılması
Öz: Fiyatlandırmada artan dalgalanmalar ve büyük kar potansiyeline sahip olan Bitcoin başta olmak üzere kripto para birimlerinin sağlam tahminini yapmak için gelişmiş makine öğrenimi teknolojilerinin kullanılması son yıllarda büyük ilgi gördü. Bu çalışmada çeşitli istatistiksel teknikler; Hareketli Ortalama Analizi ve Otoregresif Entegre Hareketli Ortalama ve makine öğrenimi (ML) teknikleri; Yapay Sinir Ağı, Tekrarlayan Sinir Ağı (RNN) ve Evrişimli Sinir Ağı, Bitcoin kripto para birimi fiyatının gelecekteki değerini tahmin etmek için uygulanmıştır ve bulunan sonuçlar karşılaştırılmıştır. Bu teknikler 35 pencere boyutu ile tek değişkenli zaman serisi analizi kapsamında uygulandı. Makine öğrenimi algoritmalarının yararlılığını kanıtlamak ve RNN sonuçlarının daha iyi olduğunu göstermek için ortalama hata karesi (MSE), ortalama mutlak hata (MAE) ve ortalama mutlak yüzde hata (MAPE) göstergeleri uygulanmıştır. Çalışma, tekrarlayan sinir ağının MSE, MAE ve MAPE ölçümleri açısından günlük Bitcoin fiyatını tahmin etmede diğer yöntemlerden daha iyi sonuçlar verdiğini ortaya koydu. Bununa birlikte, ARIMA ve makine öğrenme algoritmalarının performansını karşılaştırmak için Wilcoxon-Mann-Whitney (WMW) parametrik olmayan istatistik testi uygulanmıştır.
Anahtar Kelime: Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık
- Adcock, R., & Gradojevic, N. (2019). Non-fundamental, non- parametric Bitcoin forecasting. Physica A: Statistical Mechanics and its Applications.
- Alahmari, S. A. (2019). Using Machine Learning ARIMA to Predict the Price of Cryptocurrencies. ISeCure-The ISC International Journal of Information Security, 139-144.
- Albariqi, R., & Winarko, E. (2020). Prediction of Bitcoin Price Change using Neural Networks. International Conference on Smart Technology and Applications (ICoSTA) (s. 1-4). IEEE.
- Atsalakis, G. S., Atsalaki, I. G., Pasiouras, F., & Zopounidis, C. (2019). Bitcoin price forecasting with neuro-fuzzy techniques. European Journal of Operational Research, 770- 780.
- Ayaz, Z., Fiaidhi, J., Sabah, A., & Ansari, M. A. (2020). Bitcoin Price Prediction using ARIMA Model.
- Azari, A. (2019). Bitcoin price prediction: An ARIMA approach. arXiv preprint arXiv:1904.05315.
- 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.
- Bozdogan, H. (1987). Model selection and Akaike’s information criterion (AIC): The general theory and its analytical extensions. Psychometrika, 345-370.
- Chen, W., Xu, H., Jia, L., & Gao, Y. (2020). Machine learning model for Bitcoin exchange rate prediction using economic and technology determinants. International Journal of Forecasting, 28-43.
- Deokar, R. S., Dandage, S. M., & Jawandhiya, P. M. (2020). Design & Implementation of CryptoCurrency Prediction Using Machine Learning Approach. International Journal of Advent Research in Computer and Electronics (IJARCE), 8- 12.
- Derrac, J., García, S., Molina, D., & Herrera, F. (2011). A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm and Evolutionary Computation, 3-18.
- Dokuz, A. Ş., Çelik, M., & Ecemiş, A. (2020). Anomaly Detection in Bitcoin Prices using DBSCAN Algorithm. European Journal of Science and Technology, 436-443.
- Ellis, C. A., & Parbery, S. A. (2005). Is smarter better? A comparison of adaptive, and simple moving average trading strategies. Research in International Business and Finance, 399-411.
- Greaves, A., & Au, B. (2015). Using the Bitcoin Transaction graph to predict the price of Bitcoin. http://snap.stanford.edu/class/cs224w-2015/projects _ 2015/ adresinden alındı
- Güleryüz, D., & Özden, E. (2020). The Prediction of Brent Crude Oil Trend Using LSTM and Facebook Prophet. Avrupa Bilim ve Teknoloji Dergisi, 1-9.
- Higbee, A. (2018). The role of crypto-currency in cybercrime. Computer Fraud & Security, 13-15.
- Jalles, J. T. (2009). Structural Time Series Models and the Kalman Filter: A Concise Review.
- Khaldi, R., Afia, A. E., Chiheb, R., & Faizi, R. (2018). Forecasting of Bitcoin daily returns with EEMD-ELMAN based model. International Conference on Learning and Optimization Algorithms: Theory and Applications, (s. 1-6).
- Lahmiri, S., & Bekiros, S. (2020). Intelligent forecasting with machine learning trading systems in chaotic intraday Bitcoin market. Chaos, Solitons & Fractals.
- Li, Y., & Dai, W. (2020). Bitcoin price forecasting method based on CNN-LSTM hybrid neural network model. The Journal of Engineering, 344-347.
- Liu, M., Li, G., Li, J., Zhu, X., & Yao, Y. h. (2020). Forecasting the price of Bitcoin using deep learning. Finance Research Letters.
- Madan, I., Saluja, S., & Zhao, A. (2015). Automated bitcoin trading via machine learning algorithms. http://cs229. stanford. edu/proj2014/Isaac% 20Madan adresinden alındı
- McNally, S., Roche, J., & Caton, S. (2018). Predicting the price of bitcoin using machine learning. 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (s. 339-343). IEEE.
- Meyler, A., Kenny, G., & Quinn, T. (1998). Forecasting irish inflation using ARIMA models . Central Bank and Financial Services Authority of Ireland Technical Paper Series.
- Mudassir, M., Bennbaia, S., Unal, D., & Hammoudeh, M. (2020). Time-series forecasting of Bitcoin prices using high- dimensional features: a machine learning approach. Neural Computing and Applications, 1-15.
- Munim, Z. H., Shakil, M. H., & Alon, I. (2019). Next-day bitcoin price forecast. Journal of Risk and Financial Management.
- Nakamoto, S. (2008). Bitcoin whitepaper. https://bitcoin. org/bitcoin. pdf-(Дата обращения: 17.07. 2019).: https://bitcoin. org/bitcoin. pdf-(Дата обращения: 17.07. 2019). adresinden alındı
- Nakano, M., Takahashi, A., & Takahashi, S. (2018). Bitcoin technical trading with artificial neural network. Physica A: Statistical Mechanics and its Applications, 587-609.
- Özhan, E. (2020). Estimation Of CO2 Equivalent Greenhouse Gas Emissions In Turkey By Artificial Neural Networks And Exponential Smoothing Method. European Journal of Science and Technology, 282-289.
- Pabuçcu, H., Ongan, S., & Ongan, A. (2020). Forecasting the movements of Bitcoin prices: an application of machine learning algorithms. Quantitative Finance and Economics , 679-691.
- Phaladisailoed, T., & Numnonda, T. (2018). Machine learning models comparison for bitcoin price prediction. 10th International Conference on Information Technology and Electrical Engineering (ICITEE) (s. 506-511). IEEE.
- Refenes, A. N., Zapranis, A., & Francis, G. (1994). Stock performance modeling using neural networks: a comparative study with regression models. Neural networks, 375-388.
- Sato, R. C. (2013). Disease Management with ARIMA model in Time Series. Einstein.
- Tsai, Y. T., Zeng, Y. R., & Chang, Y. S. (2018). Air pollution forecasting using RNN with LSTM. 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 (s. 1074-1079). IEEE.
- Ulumuddin, I., Sunardi, & Fadlil, A. (2020). Bitcoin Price Prediction Using Long Short Term Memory (LSTM). JurnalMatik, 1090-1095.
- Valencia, F., Gómez-Espinosa, A., & Valdés-Aguirre, B. (2019). Price movement prediction of cryptocurrencies using sentiment analysis and machine learning. Entropy.
- Wadi, S. A. (2018). Predicting closed price time series data using ARIMA Model. Modern Applied Science.
- Yao, J., & Tan, C. L. (2000). A case study on using neural networks to perform technical forecasting of forex. Neurocomputing, 79-98.
- Yenidoğan, I., Çayir, A., Kozan, O., Dağ, T., & Arslan, Ç. (2018). Bitcoin forecasting using ARIMA and prophet. 3rd International Conference on Computer Science and Engineering (UBMK) (s. 621-624). IEEE.
- Zhang, Y. Q., & Wan, X. (2007). Statistical fuzzy interval neural networks for currency exchange rate time series prediction. Applied Soft Computing, 1149-1156.
| APA | Aygun B, Kabakçı Günay E (2021). Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns. , 444 - 454. 10.31590/ejosat.822153 |
| Chicago | Aygun Betul,Kabakçı Günay Eylül Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns. (2021): 444 - 454. 10.31590/ejosat.822153 |
| MLA | Aygun Betul,Kabakçı Günay Eylül Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns. , 2021, ss.444 - 454. 10.31590/ejosat.822153 |
| AMA | Aygun B,Kabakçı Günay E Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns. . 2021; 444 - 454. 10.31590/ejosat.822153 |
| Vancouver | Aygun B,Kabakçı Günay E Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns. . 2021; 444 - 454. 10.31590/ejosat.822153 |
| IEEE | Aygun B,Kabakçı Günay E "Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns." , ss.444 - 454, 2021. 10.31590/ejosat.822153 |
| ISNAD | Aygun, Betul - Kabakçı Günay, Eylül. "Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns". (2021), 444-454. https://doi.org/10.31590/ejosat.822153 |
| APA | Aygun B, Kabakçı Günay E (2021). Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns. Avrupa Bilim ve Teknoloji Dergisi, 0(21), 444 - 454. 10.31590/ejosat.822153 |
| Chicago | Aygun Betul,Kabakçı Günay Eylül Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns. Avrupa Bilim ve Teknoloji Dergisi 0, no.21 (2021): 444 - 454. 10.31590/ejosat.822153 |
| MLA | Aygun Betul,Kabakçı Günay Eylül Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns. Avrupa Bilim ve Teknoloji Dergisi, vol.0, no.21, 2021, ss.444 - 454. 10.31590/ejosat.822153 |
| AMA | Aygun B,Kabakçı Günay E Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns. Avrupa Bilim ve Teknoloji Dergisi. 2021; 0(21): 444 - 454. 10.31590/ejosat.822153 |
| Vancouver | Aygun B,Kabakçı Günay E Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns. Avrupa Bilim ve Teknoloji Dergisi. 2021; 0(21): 444 - 454. 10.31590/ejosat.822153 |
| IEEE | Aygun B,Kabakçı Günay E "Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns." Avrupa Bilim ve Teknoloji Dergisi, 0, ss.444 - 454, 2021. 10.31590/ejosat.822153 |
| ISNAD | Aygun, Betul - Kabakçı Günay, Eylül. "Comparison of Statistical and Machine Learning Algorithms for Forecasting Daily Bitcoin Returns". Avrupa Bilim ve Teknoloji Dergisi 21 (2021), 444-454. https://doi.org/10.31590/ejosat.822153 |
