DERİN ÖĞRENME VE EKONOMETRİK MODEL İLE BİTCOİN FİYAT TAHMİNİ: LSTM ve ARIMA

Yıl 2024, Cilt: 26 Sayı: 47, 978 - 993, 31.12.2024

Yasin Büyükkör

https://doi.org/10.18493/kmusekad.1459230

Öz

Dünyada en çok rağbet gören kripto para birimi olması nedeniyle Bitcoin (BTC), yatırımcılar ve araştırmacılar için son yıllarda dikkat çekici hale gelmiştir. Merkezi bir para birimi olmaması ve spekülasyonlara açık olması BTC fiyatında yüksek oynaklığa sebep olmaktadır. BTC fiyatının oynaklığının dikkate alınarak tahminlenmesi özellikle yatırımcılar için büyük önem taşımaktadır. Son yıllarda Makine Öğrenmesi (ML) yöntemlerinin gelişmesiyle birlikte birçok finansal alanda olduğu gibi kripto paraların fiyat tahminlemesinde sıklıkla ML yöntemlerine başvurulmaktadır. ML yöntemleri geleneksel ekonometrik yöntemlerin aksine veri setinde meydana gelen dalgalanmaları herhangi bir varsayıma ihtiyaç duymadan dikkate almakta ve çoğu zaman daha iyi sonuçlar vermektedirler. Bu çalışmada, 01.01.2018 ile 21.12.2023 tarihleri arasında BTC fiyatı geleneksel ekonometrik yöntem olan ARIMA ile ML yöntemi olan LSTM kullanılarak tahminlenmeye çalışılmıştır. Yöntemler karşılaştırılırken performans kriterleri olarak RMSE, MAE ve MAPE kriterleri kullanılmıştır. Çalışmanın sonuçlarına göre LSTM yöntemi en düşük RMSE ve MAPE değerlerine sahip olmuştur.

Anahtar Kelimeler

Bitcoin, Derin Öğrenme, Makine Öğrenmesi, Uzun Kısa Hafızalı Bellek, Finansal Zaman Serileri

BITCOIN PRICE PREDICTION USING DEEP LEARNING AND ECONOMETRIC MODEL: LSTM AND ARIMA

Öz

As the most popular cryptocurrency in the world, Bitcoin (BTC) has attracted the attention of investors and researchers in recent years. Its decentralized nature and the exposure to speculation lead to high volatility in the BTC price. Predicting the BTC price taking into account its volatility is of great importance, especially for investors. In recent years, with the development of Machine Learning (ML) methods, ML methods are frequently used in price predicting of cryptocurrencies as in many other financial areas. In contrast to traditional econometric methods, ML methods take into account the fluctuations in the data set without the making any assumptions and often give better results. In this study, the price of BTC between 01.01.2018 and 21.12.2023 is predicted using the traditional econometric method ARIMA and ML method LSTM. While comparing the methods, RMSE, MAE and MAPE criteria were used as performance criteria. According to the results of the study, LSTM method has the lowest RMSE and MAPE values.

Anahtar Kelimeler

Bitcoin, Deep Learning, Machine Learning, Long Short-Term Memory, Financial Time Series

Kaynakça

• Aggarwal, A., Gupta, I., Garg, N. ve Goel, A. (2019, August). Deep Learning Approach to Determine The Impact Of Socio Economic Factors On Bitcoin Price Prediction. In 2019 Twelfth International Conference on Contemporary Computing (IC3) (pp. 1-5). IEEE.
• Akyildirim, E., Cepni, O., Corbet, S. ve Uddin, G. S. (2023). Forecasting Mid-Price Movement of Bitcoin Futures Using Machine Learning. Annals of Operations Research, 330(1), 553-584.
• Awoke, T., Rout, M., Mohanty, L. ve Satapathy, S. C. (2020). Bitcoin Price Prediction and Analysis Using Deep Learning Models. In Communication Software and Networks: Proceedings of INDIA 2019 (pp. 631-640). Singapore: Springer Singapore.
• Box, George; Jenkins, Gwilym (1970). Time Series Analysis: Forecasting and Control. San Francisco: Holden- Day.
• Ciaian, P., Rajcaniova, M. ve Kancs, D. A. (2016). The Economics of Bitcoin Price Formation. Applied economics, 48(19), 1799-1815.
• Chen, J. (2023). Analysis Of Bitcoin Price Prediction Using Machine Learning. Journal of Risk and Financial Management, 16(1), 51.
• Chen, Z., Li, C. ve Sun, W. (2020). Bitcoin Price Prediction Using Machine Learning: An Approach to Sample Dimension Engineering. Journal of Computational and Applied Mathematics, 365, 112395.
• Cheng, J., Tiwari, S., Khaled, D., Mahendru, M. ve Shahzad, U. (2024). Forecasting Bitcoin Prices Using Artificial Intelligence: Combination Of ML, SARIMA, And Facebook Prophet Models. Technological Forecasting and Social Change, 198, 122938.
• Cocco, L., Concas, G., ve Marchesi, M. (2017). Using An Artificial Financial Market for Studying a Cryptocurrency Market. Journal of Economic Interaction and Coordination, 12, 345-365.
• Çılgın, C. ve Özdemir, M. O. (2023). Time Series Forecasting of Covid-19 Confirmed Cases in Turkey with Stacking Ensemble Models. Bingöl Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, (26), 504-520.
• de Amorim, L. B., Cavalcanti, G. D. ve Cruz, R. M. (2023). The Choice of Scaling Technique Matters For Classification Performance. Applied Soft Computing, 133, 109924.
• Demirci, E. ve Karaatlı, M. (2023). Kripto Para Fiyatlarının Lstm ve Gru Modelleri İle Tahmini. Journal of Mehmet Akif Ersoy University Economics and Administrative Sciences Faculty, 10(1), 134-157.
• Dooley, G. ve Lenihan, H. (2005). An Assessment of Time Series Methods İn Metal Price Forecasting. Resources Policy, 30(3), 208-217.
• Ediger, V. Ş. ve Akar, S. (2007). ARIMA Forecasting of Primary Energy Demand By Fuel İn Turkey. Energy policy, 35(3), 1701-1708.
• Fang, F., Chung, W., Ventre, C., Basios, M., Kanthan, L., Li, L. ve Wu, F. (2024). Ascertaining Price Formation in Cryptocurrency Markets With Machine Learning. The European Journal of Finance, 30(1), 78-100.
• Fleischer, J. P., von Laszewski, G., Theran, C. ve Parra Bautista, Y. J. (2022). Time Series Analysis of Cryptocurrency Prices Using Long Short-Term Memory. Algorithms, 15(7), 230.
• Hamayel, M. J. ve Owda, A. Y. (2021). A Novel Cryptocurrency Price Prediction Model Using GRU, LSTM And Bi- LSTM Machine Learning Algorithms. AI, 2(4), 477-496.
• Hochreiter, S. (1997). Long Short-Term Memory. Neural Computation MIT-Press.
• Hu, M. Y., Zhang, G., Jiang, C. X. ve Patuwo, B. E. (1999). A Cross‐Validation Analysis Of Neural Network Out‐Of‐ Sample Performance In Exchange Rate Forecasting. Decision Sciences, 30(1), 197-216.
• Jang, H. ve Lee, J. (2017). An Empirical Study on Modelling And Prediction Of Bitcoin Prices With Bayesian Neural Networks Based On Blockchain Information. IEEE Access, 6, 5427-5437.
• Jaquart, P., Dann, D. ve Weinhardt, C. (2021). Short-Term Bitcoin Market Prediction Via Machine Learning. The journal of finance and data science, 7, 45-66.
• Ji, S., Kim, J. ve Im, H. (2019). A Comparative Study of Bitcoin Price Prediction Using Deep Learning. Mathematics, 7(10), 898.
• Katsiampa, P. (2017). Volatility Estimation for Bitcoin: A Comparison of GARCH Models. Economics letters, 158, 3-6.
• Kercheval, A. N. ve Zhang, Y. (2015). Modelling High-Frequency Limit Order Book Dynamics with Support Vector Machines. Quantitative Finance, 15(8), 1315-1329.
• Lamothe-Fernández, P., Alaminos, D., Lamothe-López, P. ve Fernández-Gámez, M. A. (2020). Deep Learning Methods For Modeling Bitcoin Price. Mathematics, 8(8), 1245.
• Latif, N., Selvam, J. D., Kapse, M., Sharma, V. ve Mahajan, V. (2023). Comparative Performance of LSTM And ARIMA For the Short-Term Prediction Of Bitcoin Prices. Australasian Accounting, Business and Finance Journal, 17(1), 256-276.
• Liu, M., Li, G., Li, J., Zhu, X. ve Yao, Y. (2021). Forecasting The Price of Bitcoin Using Deep Learning. Finance research letters, 40, 101755.
• Maleki, N., Nikoubin, A., Rabbani, M. ve Zeinali, Y. (2023). Bitcoin Price Prediction Based On Other Cryptocurrencies Using Machine Learning And Time Series Analysis. Scientia Iranica, 30(1), 285-301.
• Mallqui, D. C. ve Fernandes, R. A. (2019). Predicting The Direction, Maximum, Minimum and Closing Prices of Daily Bitcoin Exchange Rate Using Machine Learning Techniques. Applied Soft Computing, 75, 596-606.
• Matkovskyy, R. ve Jalan, A. (2019). From Financial Markets to Bitcoin Markets: A Fresh Look At The Contagion Effect. Finance research letters, 31, 93-97.
• McIntyre, K. H. ve Harjes, K. (2016). Order Flow and The Bitcoin Spot Rate. Applied Economics and Finance, 3(3), 136-147.
• McNally, S., Roche, J. ve 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.
• Mudassir, M., Bennbaia, S., Unal, D. ve Hammoudeh, M. (2020). Time-Series Forecasting of Bitcoin Prices Using High-Dimensional Features: A Machine Learning Approach. Neural computing and applications, 1-15.
• Nakamoto, S. (2008). Bitcoin: A Peer-To-Peer Electronic Cash System. Satoshi Nakamoto.
• Oprea, S. V., Georgescu, I. A. ve Bâra, A. (2024). Is Bitcoin Ready to Be A Widespread Payment Method? Using Price Volatility and Setting Strategies for Merchants. Electronic Commerce Research, 1-39.
• Patel, K., Mehta, D., Mistry, C., Gupta, R., Tanwar, S., Kumar, N. ve Alazab, M. (2020). Facial Sentiment Analysis Using AI Techniques: State-Of-The-Art, Taxonomies, And Challenges. IEEE access, 8, 90495-90519.
• Patel, M. M., Tanwar, S., Gupta, R. ve Kumar, N. (2020). A Deep Learning-Based Cryptocurrency Price Prediction Scheme for Financial Institutions. Journal of information security and applications, 55, 102583.
• Peng, Y., Albuquerque, P. H. M., de Sá, J. M. C., Padula, A. J. A. ve Montenegro, M. R. (2018). The Best of Two Worlds: Forecasting High Frequency Volatility for Cryptocurrencies And Traditional Currencies With Support Vector Regression. Expert Systems with Applications, 97, 177-192.
• Rathore, R. K., Mishra, D., Mehra, P. S., Pal, O., Hashim, A. S., Shapi'i, A., ... ve Shutaywi, M. (2022). Real-World Model for Bitcoin Price Prediction. Information Processing & Management, 59(4), 102968.
• Saad, M., Choi, J., Nyang, D., Kim, J. ve Mohaisen, A. (2019). Toward Characterizing Blockchain-Based Cryptocurrencies for Highly Accurate Predictions. IEEE Systems Journal, 14(1), 321-332.
• Shin, M., Mohaisen, D. ve Kim, J. (2021, January). Bitcoin Price Forecasting Via Ensemble-Based LSTM Deep Learning Networks. In 2021 International Conference on Information Networking (ICOIN) (pp. 603-608). IEEE.
• Kaya, U., Akba, F., Medeni, İ. ve Medeni, T. (2020). Covid-19 Öncesi Ve Sonrasındaki Bitcoin Fiyat Değişimlerinin Makine Öğrenmesi, Zaman Serileri Analizi Ve Derin Öğrenme Yöntemleriyle Değerlendirilmesi. Bilişim Teknolojileri Dergisi, 13(3), 341-355.
• Urquhart, A. (2016). The Inefficiency of Bitcoin. Economics Letters, 148, 80-82.