Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Hybrid Machine Learning Model for Predicting the Direction of KOSPI Securities

코스피 방향 예측을 위한 하이브리드 머신러닝 모델

  • Hwang, Heesoo (Division of Information Communication Technology, Halla University)
  • Received : 2021.03.10
  • Accepted : 2021.06.20
  • Published : 2021.06.28
Download PDF
⟨ Previous Next ⟩

Abstract

In the past, there have been various studies on predicting the stock market by machine learning techniques using stock price data and financial big data. As stock index ETFs that can be traded through HTS and MTS are created, research on predicting stock indices has recently attracted attention. In this paper, machine learning models for KOSPI's up and down predictions are implemented separately. These models are optimized through a grid search of their control parameters. In addition, a hybrid machine learning model that combines individual models is proposed to improve the precision and increase the ETF trading return. The performance of the predictiion models is evaluated by the accuracy and the precision that determines the ETF trading return. The accuracy and precision of the hybrid up prediction model are 72.1 % and 63.8 %, and those of the down prediction model are 79.8% and 64.3%. The precision of the hybrid down prediction model is improved by at least 14.3 % and at most 20.5 %. The hybrid up and down prediction models show an ETF trading return of 10.49%, and 25.91%, respectively. Trading inverse×2 and leverage ETF can increase the return by 1.5 to 2 times. Further research on a down prediction machine learning model is expected to increase the rate of return.

과거 주가 데이터와 금융 관련 빅 데이터를 사용해 머신러닝 기법으로 주식시장을 예측하는 연구는 다양하게 있어 왔지만, HTS와 MTS를 통해 거래가 가능한 주가지수 연동 ETF가 생기면서 주가지수를 예측하는 연구가 최근 주목받고 있다. 본 논문에서는 KOSPI 연동 ETF를 거래할 목적으로 KOSPI의 상승 예측을 위한 머신러닝 모델과 하락예측을 위한 모델을 각각 구현한다. 이들 모델은 매개변수의 그리드 탐색을 통해 최적화 된다. 또한 정밀도를 개선해 ETF 거래 수익률을 높일 수 있도록 개별 모델들을 조합한 하이브리드 머신러닝 모델을 제안한다. 예측 모델의 성능은 정확도와 ETF 거래 수익률에 큰 영향을 미치는 정밀도로 평가된다. 하이브리드 상승 예측 모델의 정확도와 정밀도는 72.1 %와 63.8 %이고 하락 예측 모델은 79.8 %와 64.3 %이다. 하이브리드 하락 예측 모델에서 정밀도는 개별 모델보다 최소 14.3 %, 최대 20.5 % 개선되었다. 테스트 기간에 하이브리드 모델은 하락에서 10.49 %, 상승에서 25.91 %의 ETF 거래 수익률을 보였다. 인버스×2와 레버리지 ETF로 거래하면 수익률을 1.5 ~ 2배로 높일 수 있다. 하락예측 머신러닝 모델에 대한 추가 연구로 수익률을 더 높일 수 있을 것으로 기대한다.

Keywords

References

  1. H. Amin, H. M. Moein & E. Morteza. (2016). Stock market index prediction using artificial neural network, Journal of Economics, Finance and Administrative Science. DOI : 10.1016/j.jefas.2016.07.002.
  2. H. S. Hwang. (2019). ETF Trading Based on Daily KOSPI Forecasting Using Neural Networks, Journal of the Korea Convergence Society, 10(1), 7-12. DOI : 10.15207/JKCS.2019.10.4.001
  3. L. D. Persio & O. Honcha. (2017). Recurrent Neural Networks Approach to The Financial Forecast of Google Assets, Int. J. of Mathetics and Computers in Simulation, 11, 7-13.
  4. X. Ding, Y. Zhang, T. Liu & J. Duan. (2015). Deep Learning for Event-driven Stock Prediction, Proc. of the 24th Int. Joint Conf. on Artificial Intelligence, (pp. 2327-2333).
  5. O. Ican & T. B. Celik. (2017). Stock Market Prediction Performance of Neural Networks: A Literature Review, International Journal of Economics and Finance, 9(11), 100-108. https://doi.org/10.5539/ijef.v9n11p100
  6. M. Qiu & Y. Song. (2016). Predicting the Direction of Stock Market Index Movement Using an Optimized Artificial Neural Network Model. PloS one, 11(5), e0155133. DOI : 10.1371/journal.pone.0155133
  7. Y. Jiao & J. Jakubowicz. (2017). Predicting Stock Movement Direction with Machine Learning: An Extensive Study on S&P 500 Stocks. DOI: 10.1109/BigData.2017.8258518
  8. J. K. S. Liew & B. Mayster. (2017). Forecasting ETFs with Machine Learning Algorithms. The Journal of Alternative Investments, 20(3), 58-78. DOI : 10.2139/ssrn.2899520.
  9. H. S. Hwang. (2019). Predicting The Direction of The Daily KOSPI Movement Using Neural Networks For ETF Trades, Journal of the Korea Convergence Society, 10(4), 1-6. DOI : 10.15207/JKCS.2019.10.4.001
  10. I. K. Nti, A. F. Adekoya & B. A. Weyori. (2020). A comprehensive evaluation of ensemble learning for stock-market prediction, Journal of Big Data, 7(20), 1-40. DOI : 10.1186/s40537-020-00299-5
  11. S. Mehta, P. Rana, S. Singh, A. Sharma & P. Agarwal. (2019). Ensemble Learning Approach for Enhanced Stock Prediction, 12th Int. Conf. on Contemporary Computing(IC3). (pp. 1-5). DOI : 10.1109/IC3.2019.8844891.
  12. Z. Xiao & E. David. (2019). Predicting the daily return direction of the stock market using hybrid machine learning algorithms, Financial Innovation. 5, 5-24. DOI : 10.1186/s40854-019-0138-0.
  13. G. Samuel, N. Philip & I. Dennis. (2019). On Stock Market Movement Prediction Via Stacking Ensemble Learning Method, IEEE Conf. on Computational Intelligence for Financial Engineering & Economics. (pp. 1-8). DOI : 10.1109/CIFEr.2019.8759062.
  14. Y. Li & Y. Pan. (2020). A Novel Ensemble Deep Learning Model for Stock Prediction Based on Stock Prices and News. arXiv:2007.12620
  15. B. Weng, L. Lu, X. Wang, F. M. Megahed & W. Martinez. (2018). Predicting Short-Term Stock Prices using Ensemble Methods and Online Data Sources, Expert Systems with Applications, 112, 258-273. DOI : 10.1016/j.eswa.2018.06.016
  16. A. Singh. (2018). A Comprehensive Guide to Ensemble Learning (with Python codes). https://medium.com/analytics-vidhya/a-comprehensive-guide-to-ensemble-learning-with-python-codes-5261650bb531
  17. K. H. Lee & G. S. Jo. (1999). Expert System for Predicting Stock Market Timing Using A Candlestick Chart. Expert System With Applications, 16, 357-364. https://doi.org/10.1016/S0957-4174(99)00011-1