Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Analysis of Bitcoin Investment Strategy using Deep Learning

딥러닝을 이용한 비트코인 투자전략의 성과 분석

  • 김선웅 (국민대학교 비즈니스IT전문대학원)
  • Received : 2021.02.23
  • Accepted : 2021.04.20
  • Published : 2021.04.28
Download PDF
⟨ Previous Next ⟩

Abstract

Bitcoin prices have been soaring recently as investors flock to cryptocurrency exchanges. The purpose of this study is to predict the Bitcoin price using a deep learning model and analyze whether Bitcoin is profitable through investment strategy. LSTM is utilized as Bitcoin prediction model with nonlinearity and long-term memory and the profitability of MA cross-over strategy with predicted prices as input variables is analyzed. Investment performance of Bitcoin strategy using LSTM forecast prices from 2013 to 2021 showed return improvement of 5.5% and 46% more than market price MA cross-over strategy and benchmark Buy & Hold strategy, respectively. The results of this study, which expanded to recent data, supported the inefficiency of the cryptocurrency market, as did previous studies, and showed the feasibility of using the deep learning model for Bitcoin investors. In future research, it is necessary to develop optimal prediction models and improve the profitability of Bitcoin investment strategies through performance comparison of various deep learning models.

최근 암호화폐거래소로 투자자들이 몰리면서 비트코인 가격이 급등락하고 있다. 본 연구의 목적은 딥러닝 모형을 이용하여 비트코인의 가격을 예측하고, 투자전략을 통해 비트코인의 수익성이 있는지를 분석하는 것이다. 비선형성과 장기기억 특성을 보이는 비트코인 가격 예측모형으로는 LSTM을 활용하며, 예측 가격을 입력변수로 하는 이동평균선 교차전략의 수익성을 분석하였다. 2013년부터 2021년까지의 LSTM 예측 가격을 이용한 비트코인 이동평균선 교차전략의 투자 성과는 단순 시장가격을 이용한 이동평균선 교차전략과 벤치마크전략 Buy & Hold 보다 각각 5.5%와 46% 이상의 수익률 개선 효과를 보여주었다. 최근 데이터까지 확장하여 분석한 본 연구의 결과는 기존의 연구들과 마찬가지로 암호화폐 시장의 비효율성(inefficiency)을 지지하고 있으며, 비트코인 투자자들에게는 딥러닝 모형을 이용한 투자전략의 실전 활용 가능성을 보여주었다. 향후 연구에서는 다양한 딥러닝 모형들의 성과 비교를 통해 최적의 예측모형을 개발하고 비트코인 투자전략의 수익성을 개선할 필요가 있다.

Keywords

References

  1. S. Nakamoto. (2008). Bitcoin: A peer-to-peer electronic cash system. http://www.lopp.net/pdf/bitcoin.pdf
  2. H. J. Kim. (2018). Policy trends and issues on Crypto currency of Japanese government. Journal of the Korea Institute of Information and Communication Engineering, 22(10), 1398-1404. DOI : 10.6109/jkiice.2018.22.10.1398
  3. M. Vijh, D. Chandola, V. A. Tikkiwal & A. Kumar. (2020). Stock closing price prediction using machine learning techniques. Procedia Computer Science, 167, 599-606. DOI : 10.1016/j.procs.2020.03.326
  4. A. Yadav & C. K. Aditi Sharan. (2020). Optimizing LSTM for time series prediction in Indian stock market. International Conference on Computational Intelligence and Data Science, 167, 2091-2100. DOI : 10.1016/j.procs.2020.03.257
  5. D. H. Shin, K. H. Choi & C. B. Kim. (2017). Deep learning model for prediction rate improvement of stock price using RNN and LSTM. The Journal of Korean Institute of Information Technology, 15(10), 9-16. DOI : 10.14801/jkiit.2017.15.10.9
  6. J. U, P. Lu, C. Kim, U. Ryu & K. Pak. (2020). A new LSTM based reversal point prediction method using upward/downward reversal point feature sets. Chaos, Solitons and Fractals, 132, 1-15. DOI : 10.1016/j.chaos.2019.109559
  7. W. Li & J. Liao. (2017). A comparative study on trend forecasting approach for stock price time series. IEEE International Conference on Anti-counterfeiting, Security, and Identification, 74-78. DOI : 10.1109/ICASID.2017.8285747
  8. A. Moghar & M. Hamiche. (2020). Stock market prediction using LSTM recurrent neural network. Procedia Computer Science, 170, 1168-1173. DOI : 10.1016/j.procs.2020.03.049
  9. N. A. Bakar & S. Rosbi. (2017). Autoregressive integrated moving average model for forecasting cryptocurrency exchange rate in high volatility environment: A new insight of bitcoin transaction. International Journal of Advanced Engineering Research and Science, 4(11), 130-137. DOI : 10.22161/ijaers.4.11.20
  10. E. Demir, G. Gozgor, C. K. M. Lau & S. A. Vigne. (2018). Does economic policy uncertainty predict the Bitcoin returns? An empirical investigation. Finance Research Letters, 26, 145-149. DOI : 10.1016/j.frl.2018.01.005
  11. X. Li & C. Wang. (2017). The technology and economic determinants of cryptocurrency exchange rates: The case of Bitcoin. Decision Support Systems, 95, 49-60. DOI : 10.1016/j.dss.2016.12.001
  12. D. Aggarwal, S. Chandrasekaran, & B. Annamalai. (2020). A complete empirical ensemble mode decomposition ans support vector machine-based approach to predict Bitcoin prices. Journal of Behavioral and Experimental Finance, 27, 1-12. DOI : 10.1016/j.jbef.2020.100335
  13. D. Mallqui & R. Fernandes. (2019). Predicting the direction, maximum, minimum and closing prices of daily Bitcoin exchange rate using machine learning techniques. Applied Soft Computing Journal, 75, 596-606. DOI : 10.1016/j.asoc.2018.11.038
  14. M. Liu, G. Li, J. Li, X. Zhu & Y. Yao. (2020). Forecasting the price of Bitcoin using deep learning. Finance Research Letters, In press. DOI : 10.1016/j.frl.2020.101755
  15. S. Xiaolei, L. Mingxi & S. Zeqian. (2020). A novel cryptocurrency price trend forecasting model based on LightGBM. Finance Research Letters, 32, 1-6. DOI : 10.1016/j.frl.2018.12.032
  16. M. Gang, B. Kim, M. Shin, U. Baek & M. Kim. (2020). LSTM-based prediction of Bitcoin price fluctuation using sentiment analysis. Proceedings of Symposium of the Korean Institute of Communications and Information Sciences, 561-562.
  17. D. Pant, P. Neupane, A. Poudel, A. Pokhrel & B. Lama. (2018). Recurrent neural network based Bitcoin price prediction by Twitter sentiment analysis. International Conference on Computing, Communication and Security. DOI : 10.1109/CCCS.2018.85886824
  18. Y. Ahn & D. Kim. (2020). Emotional trading in the cryptocurrency market. Finance Research Letters, in Press. DOI : 10.1016/j.frl.2020.101912
  19. I. Makarov & A. Schoar. (2020). Trading and arbitrage in cryptocurrency markets. Journal of Financial Economics, 135, 293-319. DOI : 10.1016/j.jfineco.2019.07.001
  20. K. Tsang & Z. Yang. (2020). Price dispersion in bitcoin exchanges. Economics Letters, 194, 1-5. DOI : 10.1016/j.econlet.2020.109379
  21. E. Demir, G. Gozgor, C. Lau & S. Vigne. (2018). Does economic policy uncertainty predict the Bitcoin returns? An empirical investigation. Finance Research Letters, 26, 145-149. DOI : 10.1016/j.frl.2018.01.005
  22. G. Cohen. (2020). Forecasting Bitcoin trends using algorithmic learning systems. Entropy, 22, 1-11. DOI : 10.3390/e22080838
  23. Z. Chen, C. Li & W. Sun. (2020). Bitcoin price prediction using machine learning: An approach to sample dimension engineering. Journal of Computational and Applied Mathematics, 365, 1-13. DOI : 10.1016/j.cam.2019.112395
  24. S. Lahmiri & S. Bekiros. (2020). Intelligent forecasting with machine learning trading systems in chaotic intraday Bitcoin market. Chaos, Solitons and Fractals, 133, 1-7. DOI : 10.1016/j.chaos.2020.109641
  25. S. McNally, J. Roche & S. Caton. (2018). Predicting the price of Bitcoin using machine learning. 26th Euromicro International Conference on Parallel, Distributed, and Network-based Processing, 339-343. DOI : 10.1109/PDP2018.00060
  26. H. M. Kim & H. Kim. (2019). A study on predicting cryptocurrency distribution prices using machine learning techniques. Journal of Distribution Science, 10(11), 93-101. DOI : 10.13106/ijidb.2019.vol10.no11.93
  27. A. Urquhart. (2018). What causes the attention of Bitcoin?. Economics Letters, 166, 40-44. DOI : 10.1016/j.econlet.2018.02.017
  28. L. Liu. (2019). Are Bitcoin returns predictable? Evidence from technical indicators. Physica A, 533, 1-6. DOI : 10.1016/j.physa.2019.121950
  29. M. Nakano, A. Takahashi & S. Takahashi. (2018). Bitcoin technical trading with artificial neural network. Physica A, 510, 587-609. DOI : 10.1016/j.physa.2018.07.017
  30. T. L. Chen, C. H. Cheng & J. W. Liu. (2019). A causal time-series model based on multilayer perceptron regression for forecasting Taiwan stock index. International Journal of Information Technology & Decision Making, 18(6), 1967-1987. DOI : 10.1142/S0219622019500421
  31. N. Naik & B. Mohan. (2020). Intraday stock prediction based on deep neural network. National Academy Science Letters, 43, 241-246. DOI : 10.1007/s40009-019-00859-1
  32. O. Sezer & A. Ozbayoglu. (2018). Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approach. Applied Soft Computing, 70, 525-538. DOI : 10.1016/j.asoc.2018.04.024
  33. S. Hochreiter & J. Schmidhuber. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. DOI : 10.1162/neco.1997.9.8.1735
  34. J. Ilonen, J. Kamarainen & J. Lampinen. (2003). Differential evolution training algorithm for feed-forward neural networks. Neural Processing Letters, 17, 93-105. https://doi.org/10.1023/A:1022995128597
  35. H. J. Song, H. S. Choi, S. W. Kim & S. H. Oh. (2019). A study on financial time series data volatility prediction method using AI's LSTM method. Journal of Knowledge Information Technology and Systems, 14(6), 665-673. DOI : 10.34163/jkits.2019.14.6.009
  36. C. Olah. (2015). Understanding LSTM networks. https://colah.github.io/posts/2015-08-UnderstandingLSTMs/
  37. A. Bariviera. (2017). The inefficiency of Bitcoin revisited: A dynamic approach. Economics Letters, 161, 1-4. DOI : 10.1016/j.econlet.2017.09.013
  38. A. Phillip, J. Chan & S. Peiris. (2018). A new look at Cryptocurrencies. Economics Letters, 163, 6-9. DOI : 10.1016/j.econlet.2017.11.020