Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

A Study On Predicting Stock Prices Of Hallyu Content Companies Using Two-Stage k-Means Clustering

2단계 k-평균 군집화를 활용한 한류컨텐츠 기업 주가 예측 연구

  • Kim, Jeong-Woo (Dept. of Economics, Gangneung Wonju National University)
  • 김정우 (강릉원주대학교 경제학과)
  • Received : 2021.04.19
  • Accepted : 2021.07.20
  • Published : 2021.07.28
Download PDF
⟨ Previous Next ⟩

Abstract

This study shows that the two-stage k-means clustering method can improve prediction performance by predicting the stock price, To this end, this study introduces the two-stage k-means clustering algorithm and tests the prediction performance through comparison with various machine learning techniques. It selects the cluster close to the prediction target obtained from the k-means clustering, and reapplies the k-means clustering method to the cluster to search for a cluster closer to the actual value. As a result, the predicted value of this method is shown to be closer to the actual stock price than the predicted values of other machine learning techniques. Furthermore, it shows a relatively stable predicted value despite the use of a relatively small cluster. Accordingly, this method can simultaneously improve the accuracy and stability of prediction, and it can be considered as the new clustering method useful for small data. In the future, developing the two-stage k-means clustering is required for the large-scale data application.

본 연구는 기존의 k-평균 군집화를 활용한 2단계 k-평균 군집화 방법을 사용하여 한류콘텐츠 기업들의 주식가격을 예측함으로써 본 기법이 예측성능을 개선할 수 있음을 보이고자 하였다. 이를 위하여 본 연구는 2단계 k-평균 군집화의 알고리즘을 소개하고, 다양한 머신러닝 기법들과의 예측값 비교를 통하여 본 기법의 예측성능을 검증하였다. 본 기법은 기존의 k-평균 군집화로부터 얻어진 군집들 중에서 예측 대상에 근접한 군집을 추출하고 이 군집에 k-평군 군집화 방법을 다시 적용하여 실제 값에 보다 근접한 군집을 탐색하는 방식이다. 본 기법을 한류콘텐츠 기업들의 주가 시계열 자료에 적용한 결과, 다른 머신러닝 기법의 예측값들보다 실제 주식가격에 근접한 예측값을 나타내어, 기존의 k-평균 군집화 방법보다 개선된 예측성능을 보였다. 또한, 본 기법은 상대적으로 적은 크기의 군집을 사용함에도 불구하고 비교적 안정적인 예측값을 나타내었다. 이에 따라, 2단계 k-평균 군집화 기법은 예측의 정확성과 안정성을 동시에 개선할 수 있으며, 소규모 자료에도 유용할 수 있는 새로운 군집화 방식을 제시했다고 볼 수 있다. 향후에는 본 기법을 발전시켜 대규모 자료에도 적용하는 방안을 검토하는 연구가 요구된다.

Keywords

Acknowledgement

This study was supported by 2021 Academic Research Support Program in Gangneung-Wonju National University.

References

  1. T. Hastie, R. Tibshirani & J. Friedman. (2009). The Elements Of Statistical Learning: Data Mining, Inference, And Prediction. International Statistical Review, 77(3), 463-482. DOI : 10.1111/j.1751-5823.2009.00095_18.x
  2. S. Y. Kwon, Y. W. Ko & M. H. Hwang. (2010). The Market Reaction to Management Earnings Forecasts and its Determinants. Korean Management Review, 39(4), 995-1021.
  3. J. Y. Heo & J. Y. Yang. (2015). SVM based Stock Price Forecasting Using Financial Statements. KIISE Transactions on Computing Practices, 21(3), 167-172. DOI : 10.5626/KTCP.2015.21.3.167
  4. J. M. Park, G. H. Kim & N. C. Kang. (2015). The Market Reaction on the Corrective Disclosure of Management Earnings Forecasts. Korean International Accounting Review, 64, 183-200.
  5. J. B. Kim. (2012. 9. 17). Venture start-up fever, light and dark. Electronic Times News.
  6. H. Y. Jung. (2020. 6. 4). Bio-Pharmaceutical Companies, Individuals Still Invest. ChosunBiz.
  7. W. S. Jung. (2020. 4. 20). Young people in their 20s with the highest percentage of "invest in stocks"... Negative bankbook debt growth rate is also 75% "highest". The Kyunghyang Shinmun.
  8. S. S. Kim, D. W. Nam, H. Jo & S. H. Kim. (2012). A study on the relation of web news and stock price. Journal of Information Technology Service, 11(3), 191-203. DOI : 10.9716/KITS.2012.11.3.191.
  9. D. Y. Kim, J. W. Park & J. H. Choi. (2014). A comparative study between stock price prediction models using sentiment analysis and machine learning based on SNS and news articles. Journal of Information Technology Service, 13(3), 221-233. DOI : 10.9716/KITS.2014.13.3.221.
  10. S. Shin, H. J. Lee, & J. J. Ahn. (2018). A study on initial price change prediction of IPO shares using non-financial information. Journal of the Korean Data And Information Science Society, 29(2), 425-439.. https://doi.org/10.7465/jkdi.2018.29.2.425
  11. M. A. Tayal & M. M. Raghuwanshi. (2010). Review on various clustering methods for the image data. Journal of Emerging Trends in Computing and Information Sciences, 2, 34-38.
  12. F. Cai, N. A. Le-Khac & M. T. Kechadi. (2012). Clustering Approaches for Financial Data Analysis. in Conference: 8th International conference on Data Mining. Nevada : USA.
  13. I. C. Park, O. J. Kwon & T. Y. Kim. (2009). KOSPI directivity forecasting by time series model. Journal of the Korean Data And Information Science Society, 20(6), 991-998.
  14. S. Kim & J. A Kim. (2009). Analyzing financial time series data using the GARCH model. Journal of the Korean Data And Information Science Society, 20(3), 475-483.
  15. H. J. Song & S. J. Lee. (2018). A study on the optimal trading frequency pattern and forecasting timing in real time stock trading using deep learning: focused on KOSDAQ. The Journal of Information Systems, 27(3), 123-140. DOI : 10.5859/KAIS.2018.27.3.123
  16. D. S. Song. (2002). An empirical study on the effects of accounting information in kosdaq firms on the stock price. Asia Pacific Journal of Samall Business, 24(4), 79-98.
  17. A. J. O'connor. (2013). The power of popularity: An empirical study of the relationship between social media fan counts and brand company stock prices. Social Science Computer Review, 31(2), 229-235. https://doi.org/10.1177/0894439312448037
  18. M. J. Kim, J. H. Ryu, D. H. Cha & M. K. Sim. (2020). Stock price prediction using sentiment analysis: from "stock discussion room in naver. The Journal of Society for e-Business Studies, 25(4), 61-75. DOI : 10.7838/JSEBS.2020.25.4.061.
  19. J. MacQueen. (1967). Some methods for classification and analysis of multivariate observations. in Proceedings of the fifth Berkeley symposium on mathematical statistics and probability. (Vol. 1, No. 14, pp. 281-297). Oakland : USA.
  20. O. Oyelade, O. O. Oladipupo & I. Obagbuwa. (2010). Application of k Means Clustering algorithm for prediction of Students Academic Performance. International Journal of Computer Science and Information Security, 7(1), 292-295.
  21. N. Nidheesh, K. A. Nazeer & P. Ameer. (2017). An enhanced deterministic K-Means clustering algorithm for cancer subtype prediction from gene expression data. Computers in biology and medicine, 91, 213-221. DOI : 10.1016/j.compbiomed.2017.10.014
  22. R. P. D. Nath, H. J. Lee, N. K. Chowdhury & J. W. Chang. (2010). Modified K-means clustering for travel time prediction based on historical traffic data. In International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, Springer. (pp. 511-521). DOI : 10.1007/978-3-642-15387-7_55
  23. R. Shinde, S. Arjun, P. Patil & J. Waghmare. (2015). An intelligent heart disease prediction system using k-means clustering and Naive Bayes algorithm. International Journal of Computer Science and Information Technologies, 6(1), 637-639.
  24. Y. C. Lee. (2011). Clustering-based Performance Prediction Model Using Technology Rating Data. Journal of The Korean Data Analysis Society, 13(3), 1471-1482.
  25. W. Chen, S. Chen, H. Zhang & T. Wu (2017). A hybrid prediction model for type 2 diabetes using K-means and decision tree. In 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), IEEE. (pp. 386-390). DOI : 10.1109/ICSESS.2017.8342938
  26. A. Jamal, A. Handayani, A. Septiandri, E. Ripmiatin & Y. Effendi. (2018). Dimensionality reduction using pca and k-means clustering for breast cancer prediction. Lontar Komput. J. Ilm. Teknol. Inf, 9(3), 192-201. DOI : 10.24843/LKJITI.2018.v09.i03.p08
  27. K. Benmouiza & A. Cheknane. (2013). Forecasting hourly global solar radiation using hybrid k-means and nonlinear autoregressive neural network models. Energy Conversion and Management, 75, 561-569. DOI : 10.1016/j.enconman.2013.07.003
  28. M. H. Huh. (2000). Double k - means clustering. The Korean Journal of Applied Statistics, 13(2), 343-352.
  29. L. Nanetti, L. Cerliani, V. Gazzola, R. Renken & C. Keysers. (2009). Group analyses of connectivity-based cortical parcellation using repeated k-means clustering. Neuroimage, 47( 4), 1666-1677. DOI : 10.1016/j.neuroimage.2009.06.014
  30. H. Ismkhan. (2018). I-k-means?+: An Iterative Clustering Algorithm Based on an Enhanced Version of the k-kmeans. Pattern Recognition, 79, 402.-413. DOI : 10.1016/j.patcog.2018.02.015
  31. R. Salman, V. Kecman, Q. Li, R. Strack & E. Test. (2011). Two-Stage Clustering with k-Means Algorithm. Communications in Computer and Information Science, 162, 110-122. DOI : 10.1007/978-3-642-21937-5_11
  32. N. Chayangkoon & A. Srivihok. (2016). Two Step Clustering Model for K-Means Algorithm. Proceedings of the Fifth International Conference on Network, Communication and Computing-ICNCC. DOI : 10.1145/3033288.3033347
  33. A. Singh, A. Yadav & A. Rana. (2013). K-means with Three different Distance Metrics. International Journal of Computer Applications, 67(10), 13-17. DOI : 10.5120/11430-6785
  34. E. Xing, M. Jordan, S. J. Russell & A. Ng. (2002). Distance metric learning with application to clustering with side-information. Advances in neural information processing systems, 15, 521-528. DOI:10.5120/11430-6785
  35. S. A. Fahad & M. M. Alam. (2016). A modified K-means algorithm for big data clustering. International Journal of Science, Engineering and Computer Technology, 6(4), 129-132.
  36. V. Cherkassky & Y. Ma. (2004). Practical selection of SVM parameters and noise estimation for SVM regression. Neural networks, 17(1), 113-126. DOI : 10.1016/S0893-6080(03)00169-2
  37. M. Bank, M. Larch & G. Peter. (2011). Google search volume and its influence on liquidity and returns of German stocks. Finance Markets and Portfolio Management, 25(3), 239-264. DOI : 10.1007/s11408-011-0165-y