The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of stock prices using deep neural network models including an emotional predictor based on online news by industrial groups

산업군별 온라인 뉴스에 기초한 감성 예측변수를 포함하는 심층 신경망모형에 의한 주가 예측

  • Received : 2020.04.28
  • Accepted : 2020.06.11
  • Published : 2020.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

We used a deep neural network model for the prediction of the stock prices of Kia Motors and Shinsegae as listed in the KOSPI 100. We used an emotional variable derived from online news in addition to the various technical indicators most often used. The emotional variable used as a predictor variable was generated from the average of the emotional scores for companies in the industrial group after building an emotional dictionary specific to each industrial group classified in a social network analysis. The study was conducted with various combinations of predictors and confirmed that good predictive and profitable power could be expected when jointly using technical indicators and an emotional variable based on online news by industrial groups.

본 연구에서는 심층 신경망모형을 사용하여 KOSPI 100의 개별 종목인 기아차 및 신세계의 주가를 예측하였다. 예측변수로는 흔히 사용되었던 기술적 변수들과 함께 온라인 뉴스로부터 도출된 감성변수를 사용하였다. 특히 소셜 네트워크 분석을 활용하여 분류된 산업군에 특화된 감성사전을 구축한 후, 감성분석을 통하여 산업군에 속하는 각 기업들의 감성점수의 평균을 산업군 감성변수로 생성하였다. 여러 예측변수들의 조합으로 이루어진 모형들 중에서 기술적 변수와 산업군의 온라인 뉴스에 기초한 감성변수를 함께 사용하였을 때 우수한 예측력과 수익률을 보여주었다.

Keywords

References

  1. Choi, I. J. (2016). Prediction of stock fluctuation using web news text mining, Pukyong National University Master's Thesis.
  2. Jeong, J. S., Kim, D. S., and Kim, J. W. (2015). Influence analysis of internet buzz to corporate performance:individual stock price prediction using sentiment analysis of online news, Journal of Intelligence and Information Systems, 21, 37-51. https://doi.org/10.13088/jiis.2015.21.4.037
  3. Kim, D. Y. and Lee, Y. I. (2018). News based Stock Market Sentiment Lexicon Acquisition UsingWord2Vec, The Korean Journal of Bigdata, 3, 13-20. https://doi.org/10.36498/kbigdt.2018.3.1.13
  4. Kim, J. B. and Kim, H. J. (2017). A domain-specific sentiment lexicon construction method for stock index directionality, Journal of Digital Contents Society, 18, 585-592. https://doi.org/10.9728/dcs.2017.18.3.585
  5. Kim, Y. S. (2012). News big data opinion mining model for predicting KOSPI movement, Kookmin University Master's Thesis.
  6. Lee, M. and Lee, H. J. (2017). Stock price prediction by utilizing category neutral terms: text mining approach, Journal of Intelligence and Information Systems, 23, 123-138. https://doi.org/10.13088/jiis.2017.23.2.123
  7. Manning, C. D., Raghavan, P., and Schutze, H. (2009). Introduction to Information Retrieval: Scoring, term weighting, and the vector space model, Cambridge University Press.
  8. Seong, N. and Nam, K. (2018). Online news-based stock price forecasting considering homogeneity in the industrial sector, Journal of Intelligence and Information Systems, 24, 1-19.
  9. Shynkevich, Y., McGinnity, T. M., Coleman, S. A., and Belatreche, A. (2016). Forecasting movements of health-care stock prices based on different categories of news articles using multiple kernel learning, Decision Support Systems, 85, 74-83. https://doi.org/10.1016/j.dss.2016.03.001