Journal of Korean Society of Industrial and Systems Engineering (산업경영시스템학회지)

Society of Korea Industrial and System Engineering (한국산업경영시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Cryptocurrency Auto-trading Program Development Using Prophet Algorithm

Prophet 알고리즘을 활용한 가상화폐의 자동 매매 프로그램 개발

  • Hyun-Sun Kim (Department of Investment Information Engineering, Yonsei University) ;
  • Jae Joon Ahn (Division of Data Science, Yonsei University)
  • 김현선 (연세대학교 투자정보공학 협동과정) ;
  • 안재준 (연세대학교 데이터사이언스학부)
  • Received : 2023.03.22
  • Accepted : 2023.03.29
  • Published : 2023.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, research on prediction algorithms using deep learning has been actively conducted. In addition, algorithmic trading (auto-trading) based on predictive power of artificial intelligence is also becoming one of the main investment methods in stock trading field, building its own history. Since the possibility of human error is blocked at source and traded mechanically according to the conditions, it is likely to be more profitable than humans in the long run. In particular, for the virtual currency market at least for now, unlike stocks, it is not possible to evaluate the intrinsic value of each cryptocurrencies. So it is far effective to approach them with technical analysis and cryptocurrency market might be the field that the performance of algorithmic trading can be maximized. Currently, the most commonly used artificial intelligence method for financial time series data analysis and forecasting is Long short-term memory(LSTM). However, even t4he LSTM also has deficiencies which constrain its widespread use. Therefore, many improvements are needed in the design of forecasting and investment algorithms in order to increase its utilization in actual investment situations. Meanwhile, Prophet, an artificial intelligence algorithm developed by Facebook (META) in 2017, is used to predict stock and cryptocurrency prices with high prediction accuracy. In particular, it is evaluated that Prophet predicts the price of virtual currencies better than that of stocks. In this study, we aim to show Prophet's virtual currency price prediction accuracy is higher than existing deep learning-based time series prediction method. In addition, we execute mock investment with Prophet predicted value. Evaluating the final value at the end of the investment, most of tested coins exceeded the initial investment recording a positive profit. In future research, we continue to test other coins to determine whether there is a significant difference in the predictive power by coin and therefore can establish investment strategies.

Keywords

References

  1. Ammer, M.A. and Aldhyani, T.H.H., Deep Learning Algorithm to Predict Cryptocurrency Fluctuation Prices: Increasing Investment Awareness, ELECTRONICS, 2022, Vol. 11, No. 15, p. 2349.
  2. Binance, https://www.binance.com/en/markets/spot-USDT.
  3. Hochreiter, S. and Schmidhuber, J., Long short-term memory, Neural Computation, 1997, Vol. 9, No. 8, pp. 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  4. HYPERCONNECT, https://hyperconnect.github.io/2020/03/09/prophet-package.html
  5. Ilonen, J., Kamarainen, J.K., and Lampinen, J., Differential evolution training algorithm for feed-forward neural networks, Neural Processing Letters, 2003, Vol. 17, pp. 93-105. https://doi.org/10.1023/A:1022995128597
  6. Jin, Y.H., Ji, S.H., and Han, K.H., Time Series Data Analysis and Prediction System Using PCA, Journal of The Korea Convergence Society, 2021, Vol. 12. No. 11, pp. 99-107.
  7. Kim, H.Y. and Won, C.H., Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models, Expert Systems with Applications, 2018, Vol. 103, pp. 25-37. https://doi.org/10.1016/j.eswa.2018.03.002
  8. Kim, S.W., Performance Analysis of Bitcoin Investment Strategy using Deep Learning, Journal of the Korea Convergence Society, 2021, Vol. 12, No. 4, pp. 249-258.
  9. Kim, S.W., Prediction Performance of Altcoin Price using Machine Learning Algorithm, Journal of Digital Contents Society, 2023, Vol. 24, No. 1, pp. 141-151. https://doi.org/10.9728/dcs.2023.24.1.141
  10. Lee, K.H., A news event driven approach for LSTM-based stock index volatility forecasting, [master's thesis], [Seoul, Korea]: Yonsei University, 2020.
  11. Livieris, I.E., Pintelas, E., and Pintelas, P., A CNN-LSTM model for gold price time-series forecasting, Neural Computing and Applications, 2020, Vol. 32, pp. 17351-17360. https://doi.org/10.1007/s00521-020-04867-x
  12. Naver blog, https://blog.naver.com/jinp7/223005431267.
  13. Olah, C., Understanding LSTM networks, 2015, https://colah.github.io/posts/2015-08-Understanding-LSTMs/
  14. Sean, J., Taylor and Benjamin Letham., Forecasting at scale, The American Statistician, 2018, Vol. 72, No. 1, pp. 37-45. https://doi.org/10.1080/00031305.2017.1380080
  15. Song, H.J., Choi, H.S., Kim, S.W., and Oh., S.H., A study on financial time series data volatility prediction method using AI's LSTM method, Journal of Knowledge Information Technology and Systems, 2019, Vol. 14, No. 6, pp. 665-673. https://doi.org/10.34163/jkits.2019.14.6.009