Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Predicting The Direction of The Daily KOSPI Movement Using Neural Networks For ETF Trades

신경회로망을 이용한 일별 KOSPI 이동 방향 예측에 의한 ETF 매매

  • Hwang, Heesoo (Department of Electrical and Electronic Engineering, Halla University)
  • 황희수 (한라대학교 전기전자공학과)
  • Received : 2019.02.20
  • Accepted : 2019.04.20
  • Published : 2019.04.28
Download PDF
⟨ Previous Next ⟩

Abstract

Neural networks have been used to predict the direction of stock index movement from past data. The conventional research that predicts the upward or downward movement of the stock index predicts a rise or fall even with small changes in the index. It is highly likely that losses will occur when trading ETFs by use of the prediction. In this paper, a neural network model that predicts the movement direction of the daily KOrea composite Stock Price Index (KOSPI) to reduce ETF trading losses and earn more than a certain amount per trading is presented. The proposed model has outputs that represent rising (change rate in index ${\geq}{\alpha}$), falling (change rate ${\leq}-{\alpha}$) and neutral ($-{\alpha}$ change rate < ${\alpha}$). If the forecast is rising, buy the Leveraged Exchange Traded Fund (ETF); if it is falling, buy the inverse ETF. The hit ratio (HR) of PNN1 implemented in this paper is 0.720 and 0.616 in the learning and the evaluation respectively. ETF trading yields a yield of 8.386 to 16.324 %. The proposed models show the better ETF trading success rate and yield than the neural network models predicting KOSPI.

신경회로망은 과거 데이터로부터 유용한 정보를 추출해서 주가지수의 이동 방향을 예측하는데 사용되어 왔다. 주가 지수의 상승 또는 하락 방향을 예측하는 기존 연구는 지수의 작은 변화에도 상승이나 하락을 예측하므로 이를 기반으로 지수 연동 ETF를 매매 하면 손실이 발생할 가능성이 높다. 본 논문에서는 ETF 매매 손실을 줄이고 매매 당 일정 이상의 수익을 내기 위한 일별 KOrea composite S0tock Price Index (KOSPI)의 이동 방향을 예측하는 신경회로망 모델을 제안한다. 제안된 모델은 이동 방향 예측을 위해 전일 대비 지수 변동률이 상승(변동률${\geq}{\alpha}$), 하락(변동률${\leq}-{\alpha}$)과 중립($-{\alpha}$<변동률<${\alpha}$)을 표시하는 출력을 갖는다. 예측이 상승이면 레버리지 Exchange Traded Fund (ETF)를, 하락이면 인버스 ETF를 매수한다. 본 논문에서 구현된 신경회로망 모델 중 PNN1의 Hit ratio (HR)은 학습에서 0.720, 평가에서 0.616이다. 평가용 데이터로 ETF 매매를 시뮬레이션하면 수익률은 8.39 ~ 16.32 %를 보인다. 또한 제안된 이동 방향 예측 신경회로망 모델이 주가지수 예측 신경회로망 모델 보다 ETF 매매 성공률과 수익률에서 더 우수하다.

Keywords

OHHGBW_2019_v10n4_1_f0001.png 이미지

Fig. 1. Architecture of the neural network

OHHGBW_2019_v10n4_1_f0002.png 이미지

Fig. 2. Trading interval for buying leverage and inverse ETFs

OHHGBW_2019_v10n4_1_f0003.png 이미지

Fig. 3. ETF trades using PNN1 in evaluation

OHHGBW_2019_v10n4_1_f0004.png 이미지

Fig. 4. ETF trades using PNN2 in evaluation

OHHGBW_2019_v10n4_1_f0005.png 이미지

Fig. 5. ETF trades using PNN3 in evaluation

Table 1. Input variables of the neural network model

OHHGBW_2019_v10n4_1_t0001.png 이미지

Table 2. Output variables of the neural network model

OHHGBW_2019_v10n4_1_t0002.png 이미지

Table 3. The correlation coefficients of KOSPI, KOSPI200 and F-KOSPI200

OHHGBW_2019_v10n4_1_t0003.png 이미지

Table 4. Neural network parameters for the KOSPI prediction models

OHHGBW_2019_v10n4_1_t0004.png 이미지

Table 5. KOSPI prediction errors

OHHGBW_2019_v10n4_1_t0005.png 이미지

Table 6. Trade performance of the proposed models

OHHGBW_2019_v10n4_1_t0006.png 이미지

Table 7. Trade profit of the proposed models

OHHGBW_2019_v10n4_1_t0007.png 이미지

References

  1. W. Huang, Y. Nakamori & S. Y. Wang. (2005). Forecasting Stock Market Movement Direction with Support Vector Machine, Computers & Operations Research, 32(10), 2513-2522. https://doi.org/10.1016/j.cor.2004.03.016
  2. R. C. Cavalcante, R. C. Brasileiro, V. L. F. Souza, J. P. Nobrega & A. L. I. Oliveira. (2016). Computational Intelligence and Financial Markets: A Survey and Future Directions," Expert Systems with Applications, 55, 194-211. https://doi.org/10.1016/j.eswa.2016.02.006
  3. H. Amin, H. M. Moein & E. Morteza. (2016). Stock market index prediction using artificial neural network, Journal of Economics, Finance and Administrative Science. 10.1016/j.jefas.2016.07.002.
  4. Heesoo Hwang. (2018). Daily Stock Price Forecasting Using Deep Neural Network Model, Journal of the Korea Convergence Society, 9(6), 39-44. https://doi.org/10.15207/JKCS.2018.9.6.039
  5. Heesoo Hwang. (2019). ETF Trading Based on Daily KOSPI Forecasting Using Neural Networks, Journal of the Korea Convergence Society, 10(1), 7-12. https://doi.org/10.15207/JKCS.2019.10.1.007
  6. 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.
  7. X. Ding X, Y. Zhang, T. Liu & J. Duan. (2015). Deep Learning for Event-driven Stock Prediction, Proc. of the 24th Int. Joint Conf. on Artificial Intelligence, 2327-2333.
  8. Qiu M, Song Y (2016) Predicting the Direction of Stock Market Index Movement Using an Optimized Artificial Neural Network Model. https://doi.org/10.1371/journal.pone.0155133
  9. T. Chandima & M. Sidney, M.. Musa & H. Cameron. (2007). Predicting stock market index trading signals using neural networks. Pro. of the 14th Annual Global Finance Conference (GFC'07), 171-179.
  10. Rasika Yatigammana, et. al, (2018). Modelling and Forecasting Stock Price Movements with Serially Dependent Determinants, Risks, 6(52), doi:10.3390/risks6020052
  11. 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
  12. Seunghee Koh. (2016). A Converging Approach on Investment Strategies, Past Financial Information, and Investors' Behavioral Bias in the Korean Stock Market, Journal of the Korea Convergence Society, 7(6), 205-212. https://doi.org/10.15207/JKCS.2016.7.6.205
  13. L. J. Kyung-Soo & M. Boris. (2017). Forecasting ETFs with Machine Learning Algorithms. http://dx.doi.org/10.2139/ssrn.2899520.
  14. 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
  15. L. C. H. Leon, A. Liu & W. S. Chen. (2006). Pattern Discovery of Fuzzy Time Series for Financial Prediction, IEEE Trans. Knowledge and Data Engineering, 18(5), 613-625. https://doi.org/10.1109/TKDE.2006.80
  16. M. F. Moller. (1993). A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning, Neural Networks, 6, 525-533. https://doi.org/10.1016/S0893-6080(05)80056-5