Comparative Performance of Machine Learning Ensemble Algorithms for Forecasting Cryptocurrency Prices

Document Type : Original Article

Authors

1 Informatics and Systemology Department, Institute Information Technologies in Economics, Kyiv National Economic University named after Vadim Hetman, Kyiv, Ukraine

2 International E-commerce and Hotel & Restaurant Business Department, V. N. Karazin Kharkiv National University, Kharkiv, Ukraine

3 KhrustalovaDepartment of Computer-Integrated Technologies, Automation and Mechatronics, Kharkiv National University of Radio Electronics, Kharkiv, Ukraine

4 Department of Economics and Management of Industrial and Commercial Business, Ukrainian State University of Railway Transport, Ukraine

5 Department of Computer-Integrated Technologies, Automation and Mechatronics, Kharkiv National University of Radio Electronics, Kharkiv, Ukraine

Abstract

This paper discusses the problems of short-term forecasting of cryptocurrency time series using a supervised machine learning (ML) approach. For this goal, we applied two of the most powerful ensemble methods including Random Forests (RF) and Stochastic Gradient Boosting Machine (SGBM). As the dataset was collected from daily close prices of three of the most capitalized coins: Bitcoin (BTC), Ethereum (ETH) and Ripple (XRP), and as features we used  past price information and technical indicators (moving average). To check the effectiveness of these models we made an out-of-sample forecast for selected time series by using the one step ahead technique. The accuracy rate of the forecasted prices by using RF and GBM were calculated. The results verify the applicability of the ML ensembles approach for the forecasting of cryptocurrency prices. The out of sample accuracy of short-term prediction daily close prices obtained by the SGBM and RF in terms of Mean Absolut Percentage Error (MAPE) for the three most capitalized cryptocurrencies (BTC, ETH, and XRP) were within 0.92-2.61 %.

Keywords

References

  1. Coinmarketcap, Crypto-Currency Market Capitalizations. https://coinmarketcap.com/ currencies. Accessed: 15 May 2020.
  2. Krugman P.,  Bits and Barbarism. http://www.nytimes.com/2013/12/23/opinion/krugmanbits-and-barbarism.html. Accessed: 15 May 2020.
  3. CNBC, Top Economists Stiglitz, Roubini and Rogoff Renew Bitcoin Doom Scenarios. https://www.cnbc.com/2018/07/09/nobel-prize-winning-economist-joseph-stiglitz-criticizes-bitcoin.html. Accessed: 15 May 2020.
  4. Selmi, R., Tiwari, A., Hammoudeh, S., “Efficiency or speculation? A dynamic analysis of the Bitcoin market”, Economic Bulletin, Vol. 38, No. 4, (2018), 2037-2046. https://econpapers.repec.org/RePEc:ebl:ecbull:eb-18-00395. Accessed: 15 May 2020.
  5. Cheah, E., Fry, J.,“Speculative bubbles in Bitcoin markets? An empirical investigation into the fundamental value of bitcoin”, Economic Letters, Vol., No. 130, (2015), 32-36. doi: 10.1016/j.econlet.2015.02.029
  6. Ciaian, P., Rajcaniova, M., and  Kancs, A., “The economics of BitCoin price formation”, Applied Economics, Vol. 48, No. 19, (2016), 1799-1815. doi: 10.1080/00036846.2015.1109038
  7. Catania L., Grassi, S., “Modelling Crypto-Currencies Financial Time-Series”, CEIS Research Paper, Vol. 15, No. 8, (2017), 1-39. https://ideas.repec.org/p/rtv/ceisrp/417.html. Accessed: 15 May 2020.
  8. Soloviev, V., Belinskij, A., “Complex Systems Theory and Crashes of Cryptocurrency Market”, Communications in Computer and Information Science, Vol. 1007, (2019) 276-297. https://link.springer.com/chapter/10.1007/978-3-030-13929-2_14.
  9. Flach, P.: Machine Learning: The Art and Science of Algorithms that Make Sense of Data. Cambridge University Press. Cambridge, UK, (2012).
  10. Sheikhi, S., Kheirabadi, M. T.,  Bazzazi, A. “An Effective Model for SMS spam Detection using Content-based features and Averaged Neural network”, International Journal of Engineeringو Transactions B: Applications, Vol. 33, No. 2, (2020), 221-228. doi: 10.5829/IJE.2020.33.02B.06
  11. Kumar, S., Sahoo, G. A., “Random Forest Classifier based on Genetic Algorithm for Cardiovascular Diseases Diagnosis”, International Journal of Engineering, Transactions B: Applications, Vol. 30, No. 11, (2017), 1723-1729. doi:  10.5829/ije.2017.30.11b.13
  12. Patil, S., Phalle, V., “Fault Detection of Anti-friction Bearing using Ensemble Machine Learning Methods”, International Journal of Engineering, Transactions B: Applications, Vol. 31, No. 11, (2018), 1972-1981. doi: 10.5829/ije.2018.31.11b.22
  13. Makridakis, S., Spiliotis, E., Assimakopoulos, V., “Statistical and Machine Learning forecasting methods”, Plos one, March 27, (2018), 1-26. doi: 10.1371/journal.pone.0194889
  14. Bontempi, G., Taieb, S., Borgne, Y., “Machine Learning Strategies for Time Series Forecasting”, European Business Intelligence Summer School eBISS 2012, 62-77. Springer-Verlag. Berlin Heidelberg, (2013). doi: 10.1007/978-3-642-36318-4_3
  15. Persio, L., Honchar, O., “Multitask machine learning for financial forecasting”, International Journal of Circuits Systems and Signal Processing, Vol. 12, (2018), 444-451.
  16. Kourentzes, N., Barrow, D.K., Crone, S,F., “Neural network ensemble operators for time series forecasting”, Expert Systems with Applications, Vol. 41, No. 9, (2014), 4235-4244. doi:10.1016/j.eswa.2013.12.011
  17. Liu W, Wang Z, Liu X, Zeng N, Liu Y, Alsaadi FE., “A survey of deep neural network architectures and their applications” Neurocomputing, Vol. 234 (C), (2017), 11-26. doi:10.1016/j. neucom.2016.12.038.
  18. McNally, S., Roche, J., Caton, S. “Predicting the price of bitcoin using machine learning”, in: 2018 26th Euromicro Int. Conf. Parallel, Distrib. Network-Based Process., IEEE, (2018), 339-343. doi: 10.1109/PDP2018.2018.00060
  19. Hamid SA, Habib A., “Financial Forecasting with Neural Networks”, Academy of Accounting and Financial Studies Journal,. Vol. 18, No. 4, (2014), 37-55. https://www.abacademies.org/articles/aafsjvol1842014.pdf. Accessed: 15 May 2020.
  20. Boyacioglu, M., Baykan, O.K., “Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock Exchange”, Expert Systems with Applications, Vol. 38, No. 5, (2011), 5311-5319. doi: 10.1016/j.eswa.2010.10.027
  21. Varghade, P., Patel, R, “Comparison of SVR and Decision Trees for Financial Series Prediction”, International Journal on Advanced Computer Theory and Engineering, Vol. 1, No. 1, (2012), 101-105.
  22. Kumar, M., “Forecasting Stock Index Movement: A Comparison of Support Vector Machines and Random Forest”, SSRN Working Paper, (2006). doi: 10.2139/ssrn.876544
  23. Peng, Y., Henrique, P., Albuquerque, M., “The best of two worlds: Forecasting high frequency volatility for cryptocurrencies and traditional currencies with Support Vector Regression”, Expert Systems with Applications, Vol. 97, (2018), 177-192. doi: 10.1016/j.eswa.2017.12.004
  24. Ahmed NK, Atiya AF, Gayar NE, El-Shishiny H., “An Empirical Comparison of Machine Learning Models for Time Series Forecasting”, Econometric Reviews, Vol. 29, No. 5-6, (2010), 594-621. doi:10.1080/ 07474938.2010.481556
  25. Akyildirim, E., Goncuy, A., Sensoy, A., Prediction of Cryptocurrency Returns using Machine Learning, (2018).  https://arxiv.org/pdf/1805.08550.pdf. Accessed 15 May 2020.
  26. Amjad, M., Shah, D., “Trading Bitcoin and Online Time Series Prediction”, NIPS 2016: Time Series Workshop., (2016). http://proceedings.mlr.press/v55/amjad16.pdf (2016). Accessed 15 May 2020.
  27. Hitam, N. A., Ismail, A. R., “Comparative Performance of Machine Learning Algorithms for Cryptocurrency Forecasting”, (2018). https://www.researchgate.net/ publication/327415267. Accessed 15 May 2020.
  28. Mallqui, D., Fernandes, R. “Predicting the direction, maximum, minimum and closing prices of daily Bitcoin exchange rate using machine learning techniques”, Applied Soft Computing Journal, Vol. 75, (2019), 596-606. doi: 10.1016/j.asoc.2018.11.03
  29. Sezer, O.B., Mehmet Ugur Gudelek, M.U., Ozbayoglu, A.M. “Financial Time Series Forecasting with Deep Learning : A systematic literature review: 2005–2019”, Applied Soft Computing Journal,  Vol. 90, (2020), 106-181. doi: 10.1016/j.asoc.2020.106181
  30. Kumar, D., Rath, S.K. “Predicting the Trends of Price for Ethereum Using Deep Learning Techniques”, in: Artificial Intelligence and Evolutionary Computations in Engineering Systems, Springer, 2020, 103-114. doi: 10.1007/978-981-15-0199-9_9
  31. Yao, Y., Yi, J., and Zhai, S., “Predictive Analysis of Cryptocurrency Price Using Deep Learnin”, International Journal of Engineering & Technology, Vol. 7, No. 3, 27, (2018), 258-264. doi: 10.14419/ijet.v7i3.27.17889
  32. Chen, W., Xu, H., Jia, L., Gao, Y. “Machine learning model for Bitcoin exchange rate prediction using economic and technology determinants”, International Journal of Forecasting, (2020), (article in press). doi: 10.1016/j.ijforecast.2020.02.008
  33. Saxena, A., Sukumar, T., “Predicting bitcoin price using LSTM and compare its predictability with ARIMA model”, International Journal of Pure and Applied Mathematics, Vol. 119, No.17, (2018), 2591-2600. https://acadpubl.eu/hub/2018-119-17/3/214.pdf. Accessed: 15 May 2020.
  34. Breiman, L., Friedman, H., Olshen, R. A., & Stone, C. J., Classification and Regression Trees. Belmont, NJ. Wadsworth International Group, (1984).
  35. Breiman, L., “Random Forests”, Machine Learning,Vol. 45, (2001), 5-32. doi: 10.1023/A:1010933404324
  36. Friedman, Jerome H., “Greedy Function Approximation. A Gradient Boosting Machine”, Annals of Statistics, Vol. 29, No. 5, (2001), 1189-232. doi: 10.2307/2699986
  37. Friedman, Jerome H., “Stochastic Gradient Boosting”, Computational Statistics and Data Analysis, Vol. 38, No. 4, (1999), 367-378. doi: 10.1016/S0167-9473(01)00065-2
  38. Borges, T.A., Neves, R.N. “Ensemble of Machine Learning Algorithms for Cryptocurrency Investment with Different Data Resampling Methods”, Applied Soft Computing Journal , Vol. 90, (2020), 106-187. doi: 10.1016/j.asoc.2020.106187
  39. Chen, Z., Li, C., Sun, W. Bitcoin Price Prediction Using Machine Learning: An Approach to Sample Dimension Engineering, Journal of Computational and Applied Mathematics, Vol.  365, (2020), 112395. doi: 10.1016/j.cam.2019.112395
  40. Sun, X., Liu, M., Sima, Z. “A novel cryptocurrency price trend forecasting model based on LightGBM”, Finance Research Letters, Vol. 32, (2020), 101084. doi: doi.org/10.1016/j.frl.2018.12.032
  41. Yahoo Finance. https://finance.yahoo.com. Accessed: 15 May 2020.
  42. Guryanova, L., Yatsenko, R., Dubrovina, N., Babenko, V. “Machine Learning Methods and Models, Predictive Analytics and Applications”. Machine Learning Methods and Models, Predictive Analytics and Applications 2020: Proceedings of the Workshop on the XII International Scientific Practical Conference Modern problems of social and economic systems modelling (MPSESM-W 2020), Kharkiv, Ukraine, June 25, 2020, Vol-2649, (2020), 1-5. URL: http://ceur-ws.org/Vol-2649/
  43. Alessandretti, L., ElBahrawy, A., Aiello, L., Baronchelli, A., “Anticipating Cryptocurrency Prices Using Machine Learning”, Hindawi Complexity, (2018) doi: 10.1155/2018/8983590

 

International Journal of Engineering
Volume 34, Issue 1
TRANSACTIONS A: Basics
January 2021
Pages 140-148

Files

Cited by

Share

How to cite

Statistics