Cryptocurrency price prediction using GPR and SMOTE

Abstract

Cryptography is used by cryptocurrencies to shift money without the intervention of cen-tralized financial institutions. They are decentralized digital assets. On rapidly changing ex-changes like those for crypto currencies, it is a tremendously taxing procedure for people to keep track of many simultaneous instantaneous price changes. As a solution to this, computer software that can make fast and objective decisions by constantly observing can replace hu-mans. In this study, the closing price of Bitcoin (BTC), which has the highest volume in the crypto money system, is analyzed. In the study, in which the Gaussian Process Regression (GPR) model and the SMOTE method were used, data belonging to BTC for the period be-tween 25/07/2010 and 05/06/2022 were used as the data set. Opening price, highest-lowest price, volume, dollar index and some indicators used in technical analysis were used as input parameters. The kfold method was followed in the separation of training and test data. The data is divided into 5 subsets with kfold. The mean MAPE value was found to be 1887, and the mean R2 value was found to be 0.99977 in the models with SMOTE. In addition, the GPR model and the GPR model functions that were applied to the SMOTE method were compared by excluding the opening price, which was the price that was highest-lowest, from the data. It was carried out to determine which model performed better.

Keywords

• Bitcoin
• Cryptocurrency
• GPR
• SMOTE

References

1. REFERENCES
2. [1] McNally S, Roche J, Caton S. Predicting the Price of Bitcoin Using Machine Learning. Proc - 26th Euromicro Int Conf Parallel, Distrib Network-Based Process PDP 2018;339–343. [CrossRef]
3. [2] Zaj MM, Samavi ME, Koosha E. Measurement of Bitcoin Daily and Monthly Price Prediction Error Using Grey Model, Back Propagation Artificial Neural Network and Integrated model of Grey Neural Network. Adv Math Fin App 2022:535–553.
4. [3] Shankhdhar A, Singh AK, Naugraiya S, Saini PK. Bitcoin Price Alert and Prediction System using various Models. IOP Conf Ser Mater Sci Eng. 2021;1131:012009. [CrossRef]
5. [4] Livieris IE, Kiriakidou N, Stavroyiannis S, Pintelas P. An Advanced CNN-LSTM Model for Cryptocurrency Forecasting.
6. [5] Phaladisailoed T, Numnonda T. Machine learning models comparison for bitcoin price prediction. In: Proceedings of 2018 10th International Conference on Information Technology and Electrical Engineering: Smart Technology for Better Society, ICITEE 2018. Institute of Electrical and Electronics Engineers Inc.; 2018. p. 506–511. [CrossRef]
7. [6] Madan I, Saluja S, Zhao A, et al. Automated Bitcoin trading via machine learning algorithms. Available via DIALOG. Weizmann Inst Sci 2015. p. 1–5.
8. [7] Arslan ME, Kırcı P. Makine Öğrenmesi İle Borsa Analizi. Eur J Sci Technol 2021;1117–1120. [Turkish] [CrossRef]

9. [8] Jiang H, Hu X, Jia H. Penalized logistic regressions with technical indicators predict up and down trends. Soft Comput 2022;27:1367713688. [CrossRef] [9] Wu S, Liu Y, Zou Z, Weng TH. S_I_LSTM: stock price prediction based on multiple data sources and sentiment analysis. Conn Sci 2022;34:44–62. [CrossRef]
10. [10] Liu H. A research on stock forecasting based on principal component LSTM model. 2021 IEEE Int Conf Adv Electr Eng Comput Appl AEECA 2021;684–688. [CrossRef]
11. [11] Kilimci H, Yildirim M, Kilimci ZH. The Prediction of Short-Term Bitcoin Dollar Rate (BTC/USDT) using Deep and Hybrid Deep Learning Techniques. ISMSIT 2021 - 5th Int Symp Multidiscip Stud Innov Technol Proc 2021:633–637. [CrossRef]
12. [12] Sun M, Glabadanidis P. Can technical indicators predict the Chinese equity risk premium? Int Rev Financ 2022;22:114–142. [CrossRef]
13. [13] Mohapatra S, Mukherjee R, Roy A, Sengupta A, Puniyani A. Can ensemble machine learning methods predict stock returns for Indian Banks using technical indicators? J Risk Financ Manag 2022;15:350. [CrossRef]
14. [14] Erfanian S, Zhou Y, Razzaq A, Abbas A, Safeer AA, Li T. Predicting bitcoin (BTC) price in the context of economic theories: A machine learning approach. Entropy 2022;24:1–29. [CrossRef] [15] Yang J, De Montigny D, Treleaven P. ANN, LSTM, and SVR for Gold Price Forecasting. 2022 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr), 2022. [CrossRef]
15. [16] Provost F. Machine Learning from Imbalanced Data Sets 101 Extended Abstract; 2000.
16. [17] Zewdu T. Prediction of HIV Status in Addis Ababa using Data Mining Technology; 1998.
17. [18] López V, Fernández A, García S, et al. An insight into classification with imbalanced data: Empirical results and current trends on using data intrinsic characteristics. Inf Sci (Ny) 2013;250:113–141. [CrossRef]
18. [19] He H, Garcia EA. Learning from Imbalanced Data. IEEE Trans Knowl Data Eng 2009;21:1263–1284. [CrossRef]
19. [20] Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic minority over-sampling technique. J Artif Intell Res 2002;16:321–357. [CrossRef] [21] Arqub OA, Abo-Hammour Z. Numerical solution of systems of second-order boundary value problems using continuous genetic algorithm. Inf Sci (Ny) 2014;279:396–415. [CrossRef]
20. [22] Bollinger J. Using bollinger bands. Stock Comodities 1992;10:47–51. [CrossRef]
21. [23] Aci M, Dogansoy GA. Demand forecasting for e-retail sector using machine learning and deep learning methods. J Fac Eng Archit Gazi Univ 2022;37:1325–1339.
22. [24] Liu K, Hu X, Wei Z, Li Y, Jiang Y. Modified gaussian process regression models for cyclic capacity prediction of lithium-ion batteries. IEEE Trans Transp Electrif 2019;5:1225–1236. [CrossRef]
23. [25] Zhang N, Xiong J, Zhong J, Leatham K. Gaussian process regression method for classification for high-dimensional data with limited samples. 8th International Conference on Information Science and Technology 2018;358–363. [CrossRef] [26] Heo Y, Zavala VM. Gaussian process modeling for measurement and verification of building energy savings. Energy Build 2012;53:7–18. [CrossRef]
24. [27] Eberhard J, Geissbuhler V. Konservative und operative therapie bei harninkontinenz, deszensus und urogenital-beschwerden; 2000. [Deutsch]
25. [28] Pat S, Çelik Ö, Odabaş A, Korkmaz Ş. Optical properties of Nb2O5 doped ZnO nanocomposite thin film deposited by thermionic vacuum arc. Optik 2022;258:168928. [CrossRef]
26. [29] Zhang Y, Xu X. Yttrium barium copper oxide superconducting transition temperature modeling through gaussian process regression. Comput Mater Sci 2020;179:109583. [CrossRef]
27. [30] So B, Boucher J, Valdez EA. Synthetic dataset generation of driver telematics. Risks 2021;9:58. [CrossRef]
28. [31] Chen KY, Wang CH. Support vector regression with genetic algorithms in forecasting tourism demand. Tour Manag 2007;28:215–226. [CrossRef]
29. [32] Metin S. Kripto Para Fiyatlarının Regresyon Analizi Yöntemleri ile Tahmini: Bitcoin, Etherum ve Ripple. In: 2. Uluslararası Sosyal Bilimler ve İnovasyon Kongresi; 2021.
30. [33] Abo-Hammour Z, Alsmadi O, Momani S, Abu Arqub O. A genetic algorithm approach for prediction of linear dynamical systems. Math Probl Eng 2013;2013:831657. [CrossRef]
31. [34] Abu Arqub O, Abo-Hammour Z, Momani S, Shawagfeh N. Solving singular two-point boundary value problems using continuous genetic algorithm. In Abstract Applied Analysis. Hoboken, New Jersey, U.S.: Wiley; 2012. [CrossRef]
32. [35] Abo-Hammour Z, Abu Arqub O, Momani S, Shawagfeh N. Optimization solution of Troesch’s and Bratu’s problems of ordinary type using novel continuous genetic algorithm. Discret Dyn Nat Soc 2014;2014:115. [CrossRef]