Blockchain: Concepts, Issues, and Applications

EnglishTürkçe

CHAPTER


DOI :10.26650/B/T8SSc4.2024.041.002   IUP :10.26650/B/T8SSc4.2024.041.002    Full Text (PDF)

A Machine Learning-Based Bitcoin Price Forecasting

Nimet Melis Esenyel İçen, Sinan Demirezen, Hüseyin İçen

Challenges and limitations in the traditional economic system have paved the way for the idea of decentralization. Blockchain underlies the concept of decentralization, enabling peer-to-peer transactions without the need for intermediary institutions. Although Blockchain, known as a distributed and immutable ledger, was introduced during the Web 1.0 era, it gained significant traction with the advent of Bitcoin, the first cryptocurrency. Blockchain serves as the foundation for cryptocurrencies, which are digital assets secured using cryptography. Unlike fiat currencies, cryptocurrencies are not subject to the control of central authorities such as traditional financial institutions or governments. Since cryptocurrencies are utilized as investment tools, their prices and value forecasts hold significant importance for investors. In this chapter, we have proposed two models for forecasting Bitcoin prices, utilizing artificial neural networks and random forest regression. The first model takes into account the prices of cryptocurrencies, excluding stablecoins that are believed to impact Bitcoin prices in existing literature. On the other hand, the second model was developed using Bitcoin price, BTC dominance data, halving period, and Bitcoin hashrate variables. According to the error measurement criteria - MAPE, MAE, and MASE - the second model, forecasted with the RBP algorithm and logistic activation function, and incorporating BTC low, high prices, and dominance data halving variables, offers the best explanation for Bitcoin prices.


Keywords: Bitcoin, Cryptocurrency, Blockchain, Artificial Neural Networks, Random Forest Regression, Price Forecasting

References

  • Aggarwal, D. (2019). Do bitcoins follow a random walk model?. Research in Economics, 73(1), 15-22. google scholar
  • Almasri, E., & Arslan, E. (2018, October). Predicting cryptocurrencies prices with neural networks. In 2018 6th International Conference on Control Engineering & Information Technology (CEIT) (pp. 1-5). IEEE. google scholar
  • Arora, I. & Anju, S. (2016). Comparison of Back Propagation Training Algorithms for Software Defect Predic-tion. Proceedings of the 2016 2nd International Conference on Contemporary Computing and Informatics, IC3I 51-58. doi: 10.1109/IC3I.2016.7917934. google scholar
  • Breiman, L. (2001). Random forests. Machine Learning, 45, 5-32. google scholar
  • Brent, R. P. (1991). Fast Training Algorithms for Multilayer Neural Nets. IEEE Transactions on Neural Networks, 2(3), 346-354. google scholar
  • Chohan, U. W. (2022). A History of Bitcoin. Available at SSRN 3047875. google scholar
  • Ciaian, P., & Rajcaniova, M. (2018). Virtual relationships: Short-and long-run evidence from BitCoin and altcoin markets. Journal of International Financial Markets, Institutions and Money, 52, 173-195. google scholar
  • Coinbase. (July 27, 2023). Dogecoin. https://www.coinbase.com/tr/price/dogecoin. google scholar
  • Coinbase. (July 20, 2023). Proof of Work. https://www.coinbase.com/th/learn/crypto-basics/what-is-proof-of-work-or-proof-of-stake. google scholar
  • Coinbase. (September 10, 2023). Market Cap. https://www.coinbase.com/learn/crypto-basics/what-is-market-cap. google scholar
  • Coindesk. (2023, July 8). First bitcoin transaction. Retrieved from https://www.coindesk.com/consensus-ma-gazine/2023/01/12/remembering-hal-finney-on-the-14th-anniversary-of-the-first-bitcoin-transaction/#:~:-text=It’s%20been%2014%20years%20since,%2C%2010%20bitcoin%20(BTC). google scholar
  • CoinMarketCap. (n.d). Today’s Cryptocurrency Prices by Market Cap. Retrieved July 4, 2023. https://coinmar-ketcap.com/. google scholar
  • Garg, S. (2018). Autoregressive integrated moving average model based prediction of bitcoin close price. In 2018 international conference on smart systems and inventive technology (ICSSIT) (pp. 473-478). IEEE. google scholar
  • Garg, R. (2023). Blockchain for Real World Applications. Hoboken, NJ: John Wiley & Sons. google scholar
  • Gupta, C., & Mahajan, A. (2020, July). Evaluation of proof-of-work consensus algorithm for blockchain networks. In 2020 11th International Conference on Computing, Communication and Networking Techno-logies (ICCCNT) (pp. 1-7). IEEE. google scholar
  • Güriş, B., & Polat, B. (2022). Bitcoin, gold, DXY, and Dow-Jones asymmetric relationship: Evidence from NARDL analysis. In S. Demirci & L. Çinko (Eds.), Bitcoin, gold, DXY, and Dow-Jones asymmetric relati-onship: Evidence from NARDL analysis (pp. 85-102). Istanbul, Turkey: Der Yayınları. google scholar
  • Cutler, A., Cutler, D. R., & Stevens, J. R. (2012). Random forests. Ensemble machine learning: Methods and Applications, 157-175. google scholar
  • Dangeti, P. (2017). Statistics for Machine Learning: Techniques for Exploring Supervised. Unsupervised, and Reinforcement Learning Models with Python and R; Packt Publishing: Birmingham, UK. google scholar
  • Hashish, I. A., Forni, F., Andreotti, G., Facchinetti, T., & Darjani, S. (2019, September). A hybrid model for bitcoin prices prediction using hidden Markov models and optimized LSTM networks. In 2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) (pp. 721-728). google scholar
  • Hitam, N. A., Ismail, A. R., & Saeed, F. (2019). An optimized support vector machine (SVM) based on particle swarm optimization (PSO) for cryptocurrency forecasting. Procedia computer science, 163, 427-433. google scholar
  • Hastie, T., Tibshirani, R., Friedman, J. H., & Friedman, J. H. (2009). The elements of statistical learning: data mining, inference, and prediction (Vol. 2, pp. 1-758). New York: springer. google scholar
  • Haykin, S. (2009). Neural Networks and Learning Machines. Third Edition. Prentice Hall. 906 google scholar
  • Jain, A., Tripathi, S., Dwivedi, H. D., & Saxena, P. (2018, August). Forecasting price of cryptocurrencies using tweets sentiment analysis. In 2018 eleventh international conference on contemporary computing (IC3) (pp. 1-7). google scholar
  • Kubal, J., & Kristoufek, L. (2022). Exploring the relationship between Bitcoin price and network’s hashrate within endogenous system. International Review of Financial Analysis, 84, 102375. google scholar
  • Lahmiri, S. (2012). Resilient Back-Propagation Algorithm, Technical Analysis and the Predictability of Time Series in the Financial Industry. Decision Science Letters, 1(2), 47-52. doi: 10.5267/j.dsl.2012.09.002. google scholar
  • Li, Y., Zou, C., Berecibar, M., Nanini-Maury, E., Chan, J. C. W., Van den Bossche, P., ... & Omar, N. (2018). Ran-dom forest regression for online capacity estimation of lithium-ion batteries. Applied Energy, 232, 197-210. google scholar
  • Lin, Q., Jorge, L., Wenrong, W., Punit, B., & Markus, D. (2020). Prediction of Maximum Flood Inundation Extents with Resilient Backpropagation Neural Network: Case Study of Kulmbach. Frontiers in Earth Science, 8, 332. google scholar
  • McCaffrey, J. (2017). How to Use Resilient Back Propagation to Train Neural Networks. Visual Studio Magazine. google scholar
  • Mohanty, P., Patel, D., Patel, P., & Roy, S. (2018, August). Predicting fluctuations in cryptocurrencies’ price using users’ comments and real-time prices. In 2018 7th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions)(ICRITO) (pp. 477-482). IEEE. google scholar
  • Nakamoto, S. (2008). Bitcoin: A Peer-to-Peer Electronic Cash System. Decentralized Business Review. google scholar
  • Nawi, N. M., Ransing, R. S., & Ransing, M. R. (2008). An Improved Conjugate Gradient Based Learning Algorithm for Back Propagation Neural Networks. International Journal of Computer and Information Engineering, 2(6), 2062-2071. google scholar
  • Patel, M. M., Tanwar, S., Gupta, R., & Kumar, N. (2020). A deep learning-based cryptocurrency price prediction scheme for financial institutions. Journal of Information Security and Applications, 55, 102583. google scholar
  • Prasad, N., Rajeshni, S., & Sunil, P. L. (2013). Comparison of Back Propagation and Resilient Propagation Al-gorithm for Spam Classification. Proceedings of International Conference on Computational Intelligence, Modelling andSimulation 29-34. doi: 10.1109/CIMSim.2013.14. google scholar
  • Radityo, A., Qorib, M., & Indra, B. (2018). Prediction of Bitcoin Exchange Rate to American Dollar Using Artificial Neural Network Methods. 2017 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2017 433-437. doi: 10.1109/ICACSIS.2017.8355070. google scholar
  • Rathan, K., Sai, S. V., & Manikanta, T. S. (2019, April). Crypto-currency price prediction using decision tree and regression techniques. In 2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI) (pp. 190-194). google scholar
  • Rathore, R. K., Mishra, D., Mehra, P. S., Pal, O., Hashim, A. S., Shapi’i, A., ... & Shutaywi, M. (2022). Real-wor-ld model for bitcoin price prediction. Information Processing & Management, 59(4), 102968. google scholar
  • Riedmiller, M., & Heinrich, B. (1993). A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm. PP. 586-91 in IEEE international conference on neural networks. google scholar
  • Roy, S., Nanjiba, S., & Chakrabarty, A. (2018, December). Bitcoin price forecasting using time series analysis. In 2018 21st International Conference of Computer and Information Technology (ICCIT) (pp. 1-5). IEEE. google scholar
  • Rumelhart, D. E., & McClelland, J. (1986). Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Vol. 1. MIT press. google scholar
  • Sin, E., & Wang, L. (2017, July). Bitcoin price prediction using ensembles of neural networks. In 2017 13th International conference on natural computation, fuzzy systems and knowledge discovery (ICNC-FSKD) (pp. 666-671). IEEE. google scholar
  • Wirawan, I. M., Widiyaningtyas, T., & Hasan, M. M. (2019, September). Short term prediction on bitcoin price using ARIMA method. In 2019 International Seminar on Application for Technology of Information and Communication (iSemantic) (pp. 260-265). IEEE. google scholar
  • Wu, C. H., Lu, C. C., Ma, Y. F., & Lu, R. S. (2018, November). A new forecasting framework for bitcoin price with LSTM. In 2018 IEEE International Conference on Data Mining Workshops (ICDMW) (pp. 168-175). IEEE. google scholar
  • Yiying, W., & Yeze, Z. (2019, March). Cryptocurrency price analysis with artificial intelligence. In 2019 5th International Conference on Information Management (ICIM) (pp. 97-101). google scholar
  • Zhang, G. P. (2001). An Investigation of Neural Networks for Linear Time-Series Forecasting. Computers & Operations Research, 28(12), 1183-1202. google scholar
  • Zhengyang, W., Xingzhou, L., Jinjin, R., & Jiaqing, K. (2019, June). Prediction of cryptocurrency price dyna-mics with multiple machine learning techniques. In Proceedings of the 2019 4th International Conference on Machine Learning Technologies (pp. 15-19). google scholar


SHARE




Istanbul University Press aims to contribute to the dissemination of ever growing scientific knowledge through publication of high quality scientific journals and books in accordance with the international publishing standards and ethics. Istanbul University Press follows an open access, non-commercial, scholarly publishing.