Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Classification Algorithm-based Prediction Performance of Order Imbalance Information on Short-Term Stock Price

분류 알고리즘 기반 주문 불균형 정보의 단기 주가 예측 성과

  • Kim, S.W. (Graduate School of Business IT, Kookmin University)
  • 김선웅 (국민대학교 비즈니스IT전문대학원)
  • Received : 2022.10.14
  • Accepted : 2022.11.11
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Investors are trading stocks by keeping a close watch on the order information submitted by domestic and foreign investors in real time through Limit Order Book information, so-called price current provided by securities firms. Will order information released in the Limit Order Book be useful in stock price prediction? This study analyzes whether it is significant as a predictor of future stock price up or down when order imbalances appear as investors' buying and selling orders are concentrated to one side during intra-day trading time. Using classification algorithms, this study improved the prediction accuracy of the order imbalance information on the short-term price up and down trend, that is the closing price up and down of the day. Day trading strategies are proposed using the predicted price trends of the classification algorithms and the trading performances are analyzed through empirical analysis. The 5-minute KOSPI200 Index Futures data were analyzed for 4,564 days from January 19, 2004 to June 30, 2022. The results of the empirical analysis are as follows. First, order imbalance information has a significant impact on the current stock prices. Second, the order imbalance information observed in the early morning has a significant forecasting power on the price trends from the early morning to the market closing time. Third, the Support Vector Machines algorithm showed the highest prediction accuracy on the day's closing price trends using the order imbalance information at 54.1%. Fourth, the order imbalance information measured at an early time of day had higher prediction accuracy than the order imbalance information measured at a later time of day. Fifth, the trading performances of the day trading strategies using the prediction results of the classification algorithms on the price up and down trends were higher than that of the benchmark trading strategy. Sixth, except for the K-Nearest Neighbor algorithm, all investment performances using the classification algorithms showed average higher total profits than that of the benchmark strategy. Seventh, the trading performances using the predictive results of the Logical Regression, Random Forest, Support Vector Machines, and XGBoost algorithms showed higher results than the benchmark strategy in the Sharpe Ratio, which evaluates both profitability and risk. This study has an academic difference from existing studies in that it documented the economic value of the total buy & sell order volume information among the Limit Order Book information. The empirical results of this study are also valuable to the market participants from a trading perspective. In future studies, it is necessary to improve the performance of the trading strategy using more accurate price prediction results by expanding to deep learning models which are actively being studied for predicting stock prices recently.

투자자들은 증권회사가 제공하는 시세표인 Limit Order Book 정보를 통해 국내외 투자자들이 제출하는 주문 정보를 실시간으로 파악하면서 거래에 참여하고 있다. Limit Order Book에 실시간으로 공개되고 있는 주문 정보가 주가 예측에서 유용성이 있을까? 본 연구는 장 중 투자자들의 매수와 매도 주문이 어느 한쪽으로 쏠리면서 주문 불균형이 나타나는 경우 미래 주가 등락의 예측 변수로서 유의성이 있는지를 분석하는 것이다. 분류 알고리즘을 이용하여 주문 불균형 정보의 당일 종가 등락에 대한 예측 정확도를 높이고, 예측 결과를 이용한 데이트레이딩 전략을 제안하며 실증분석을 통해 투자 성과를 분석한다. 자료는 2004년 1월 19일부터 2022년 6월 30일까지의 4,564일 동안의 코스피200 주가지수선물 5 분 봉 주가를 분석하였다. 실증분석 결과는 다음과 같다. 첫째, 총매수 주문량과 총매도 주문량의 불균형 정도로 측정하는 주문 불균형지수와 주가는 유의적 상관성을 보인다. 둘째, 주문 불균형 정보는 당일 종가까지의 미래 주가 등락에 대해서도 유의적인 영향력이 나타났다. 셋째, 주문 불균형 정보를 이용한 당일 종가 등락의 예측 정확도는 Support Vector Machines 알고리즘이 54.1%로 가장 높게 나타났다. 넷째, 하루 중 이른 시점에서 측정한 주문 불균형지수가 늦은 시점에서 측정한 주문 불균형지수보다 예측 정확성이 더 높았다. 다섯째, 종가 등락 예측 결과를 이용한 데이트레이딩 전략의 투자 성과는 비교모형의 투자 성과보다 높게 나타났다. 여섯째, 분류 알고리즘을 이용한 투자 성과는 K-Nearest Neighbor 알고리즘을 제외하면 모두 비교모형보다 총수익 평균이 높게 나타났다. 일곱째, Logistic Regression, Random Forest, Support Vector Machines, XGBoost 알고리즘의 예측 결과를 이용한 데이트레이딩 전략의 투자 성과는 수익성과 위험성을 동시에 평가하는 샤프비율에서도 비교모형보다 높은 결과를 보여주었다. 본 연구는 Limit Order Book 정보 중 총매수 주문량과 총매도 주문량 정보의 경제적 가치가 존재함을 밝혔다는 점에서 기존의 연구와 학술적 차별점을 갖는다. 본 연구의 실증분석 결과는 시장 참여자들에게 투자 전략적 측면에서 함의가 있다고 판단된다. 향후 연구에서는 최근 활발히 연구가 진행되고 있는 딥러닝 모형 등으로의 확장을 통해 주가 예측의 정확도를 높임으로써 데이트레이딩 투자전략의 성과를 개선할 필요가 있다.

Keywords

References

  1. Berkman, H., Koch, P. D., Tuttle, L., & Zhang, Y. J. (2012). Paying attention: Overnight returns and the hidden cost of buying at the open. Journal of Financial and Quantitative Analysis, 47(4), 715-741. https://doi.org/10.1017/S0022109012000270
  2. Cao, C., Hansch, O., & Wang, X. (2009). The information content of an open limit-order book. The Journal of Futures Markets, 29(1), 16-41. https://doi.org/10.1002/fut.20334
  3. Cao, H., Lin, T., & Zhang, H. (2019). Stock price pattern prediction based on complex network and machine learning. Complexity, 2019(10), 1-12. https://doi.org/10.1155/2019/4132485
  4. Cao, L., & Tay, F. E. H. (2001). Financial forecasting using support vector machines. Neural Computing & Applications, 10, 184-192. https://doi.org/10.1007/s005210170010
  5. Cenesizoglu, Dionne, T., G., & Zhou, X. (2022). Asymmetric effects of the limit order book on price dynamics. Journal of Empirical Finance, 65, 77-98. https://doi.org/10.1016/j.jempfin.2021.11.002
  6. Chen, Y., & Hao, Y. (2017). A feature weighted support vector machine and k-nearest neighbor algorithm for stock market indices prediction. Expert Systems with Applications, 80, 340-355. https://doi.org/10.1016/j.eswa.2017.02.044
  7. Cont, R., Stoikov, & Talreja, R. (2010). A stochastic model for order book dynamics. Operations Research, 58(3), 549-563. https://doi.org/10.1287/opre.1090.0780
  8. Griffiths, M. D., Smith, B. F., Turnbull, D. A. S., & White, R. W. (2000). The costs and determinants of order aggressiveness. Journal of Financial Economics, 56(1), 65-88. https://doi.org/10.1016/S0304-405X(99)00059-8
  9. Han, S. B. (2017). Foreigners' short selling and price pressures in the Korean stock market. Journal of Industrial Economics and Business, 30(6), 2119-2139. https://doi.org/10.22558/jieb.2017.12.31.6.2119
  10. Harris, L., & Panchapagesan, V. (2005). The information content of the limit order book: Evidence from NYSE specialist trading decisions. Journal of Financial Markets, 18(1), 25-67. https://doi.org/10.1016/j.finmar.2004.07.001
  11. Kang, J., & Ryu, D. (2010). Which trades move asset prices? An analysis of futures trading data. Emerging Markets Finance & Trade, 46, 7-22. https://doi.org/10.2753/REE1540-496X4603S101
  12. Kim, S. W. (2022). Performance on Altcoin investment using technical trading rules. Journal of the Korean Academia-Industrial, 23(6), 198-207. https://doi.org/10.5762/KAIS.2022.23.6.198
  13. Kim, S. W. (2019). Performance analysis on day trading strategy with bid-ask volume. The Journal of the Korea Contents Association, 19(7), 36-46. https://doi.org/10.5392/JKCA.2019.19.07.036
  14. Kim, S. W., & Ahn, H. (2010). Development of an intelligent trading system using support vector machines and genetic algorithms. Journal of Intelligence and Information Systems, 16(1), 71-92.
  15. Kim, T. D., & Ok, K. (2015). Private information and trading behavior: KOSPI200 Futures Markets. Journal of Derivatives and Quantitative Studies, 23(2), 207-241. https://doi.org/10.1108/JDQS-02-2015-B0003
  16. Kim, Y., Choi, H. S., & Kim, S. W. (2020). A study on risk parity asset allocation model with XGBoost. Journal of Intelligence and Information Systems, 26(1), 135-149. https://doi.org/10.13088/jiis.2020.26.1.135
  17. Kozhan, R., & Salmon, M. (2012). The information content of a limit order book: The case of an FX market. Journal of Financial Markets, 15, 1-28. https://doi.org/10.1016/j.finmar.2011.07.002
  18. Kumbure, M. M., Lohrmann, C., Luukka, P., & Porras, J. (2022). Machine learning techniques and data for stock market forecasting: A literature review. Expert Systems with Applications, 197, 1-41. https://doi.org/10.1016/j.eswa.2022.116659
  19. Lee, W. B., & Choe, H. (2007). Short-term return predictability of information in the open limit order book. Asia-Pacific Journal of Financial Studies, 36(6), 963-1008.
  20. Lee, Y., & Kim, W. C. (2013). A stochastic model for order book dynamics: An application to Korean stock index futures. Management Science and Financial Engineering, 19(1), 37-41. https://doi.org/10.7737/MSFE.2013.19.1.037
  21. Lohrmann, C., & Luukka, P. (2019). Classification of intraday S&P500 returns with a random forest. International Journal of Forecasting, 35, 390-407. https://doi.org/10.1016/j.ijforecast.2018.08.004
  22. Malagrino, L., Roman, N. T., & Monteiro, A. M. (2018). Forecasting stock market index daily direction: A Bayesian network approach. Expert Systems with Applications, 105, 11-22. https://doi.org/10.1016/j.eswa.2018.03.039
  23. Park, Y. J., Kutan, A. M., & Ryu, D. (2019). The impacts of overseas market shocks on the CDS-option basis. The North American Journal of Economics and Finance, 47, 622-636. https://doi.org/10.1016/j.najef.2018.07.003
  24. Ranaldo, A. (2004). Order aggressiveness in limit order book markets. Journal of Financial Markets, 7(1), 53-74. https://doi.org/10.1016/S1386-4181(02)00069-1
  25. Ryu, D. (2013). Price impact asymmetry of futures trades: Trade direction and trade size. Emerging Markets Review, 14, 110-130. https://doi.org/10.1016/j.ememar.2012.11.005
  26. Sharpe, W. F. (1966). Mutual Fund Performance. The Journal of Business, 39(1), 119-138. https://doi.org/10.1086/294846
  27. Song, J. H., Choi, H. S., & Kim, S. W. (2017). A study on commodity asset investment model based on machine learning technique. Journal of Intelligence and Information Systems, 23(4), 127-146. https://doi.org/10.13088/jiis.2017.23.4.127
  28. Thakkar, A., & Chaudhari, K. (2022). Information fusion-based genetic algorithm with long short-term memory for stock price and trend prediction. Applied Soft Computing, 128, 1-20. https://doi.org/10.1016/j.asoc.2022.109428
  29. Wang, M. C., Zu, L. P., & Kuo, C. J. (2008). The state of the electronic limit order book, order aggressiveness and price formation. Asia-Pacific Journal of Financial Studies, 37(2), 245-296.
  30. Weng, B., Ahmed, M. A., & Megahed, F. M. (2017). Stock market one-day ahead movement prediction using disparate data sources. Expert Systems with Applications, 79, 153-163. https://doi.org/10.1016/j.eswa.2017.02.041
  31. Yang, H. (2021). Investor sentiment and market dynamics: Evidence from index futures markets. Investment Analysts Journal, 50, 258-272. https://doi.org/10.1080/10293523.2021.2010376
  32. Yun, K. K., Yoon, S. W., & Won, D. (2021). Prediction of stock price direction using a hybrid GA-XGBoost algorithm with a three-stage feature engineering process. Expert Systems with Applications, 186, 1-21. https://doi.org/10.1016/j.eswa.2021.115716
  33. Zhang, N., Lin, A., & Shang, P. (2017). Multidimensional k-nearest neighbor model based on EEMD for financial time series forecasting. Physica A, 477, 161-173. https://doi.org/10.1016/j.physa.2017.02.072
  34. Zhang, D., & Lou, S. (2021). The application research of neural network and BP algorithm in stock price pattern classification and prediction. Future Generation Computer Systems, 115, 872-879. https://doi.org/10.1016/j.future.2020.10.009