Effectiveness of Six Text Classifiers for Predicting SET Stock Price Direction

  • Ponrudee NetisopakulEmail author
  • Woranun Saewong
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1149)


Six text classification methods were compared to find the best model for predicting Stock Exchange of Thailand stock prices. News headlines, on individual stocks, were classified as causing “change” and “no-change” based on a preset change threshold, 2.5%. The training dataset was collected by matching stock news in 2018 with stock names and filling in stock price changes. 258 news were associated with a “change” and 636 news with “no-change”. The Thai text news items were preprocessed and converted to TF-IDF vector representation. Six machine learning text classification methods are applied to create six text classifier models and create a confusion matrix, then compared with actual changes to obtain accuracy scores. We found that a deep learning classifier (with 85.6% accuracy) scored better than other classifiers for one day price movement to assist short-term investments.


Stock trends Decision tree Neural network Deep learning Naive Bayes Random forest SVM Stock news Text classification 



We would like to thank the Thai NLP Group for sharing their knowledge and resources, King Mongkut’s Institute of Technology Ladkrabang (KMITL) for the research funding and KMITL KRIS for advice on technical English.


  1. 1.
    The Stock Exchange of Thailand: TSD’s Statistical Highlights (As of December). Accessed 20 Jan 2019
  2. 2.
    Cheng, S.H.: Forecasting the change of intraday stock price by using text mining news of stock. In: Proceedings of the Ninth International Conference on Machine Learning and Cybernetics, pp. 2605–2609. IEEE, Qingdao (2010)Google Scholar
  3. 3.
    Ichinose, K., Shimada, K.: Stock market prediction from news on the web and a new evaluation approach in trading. In: Proceedings of 5th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI), pp. 77–81. IEEE, Kumamoto (2016)Google Scholar
  4. 4.
    Yetis, Y., Kaplan, H., Jamshidi, M.: Stock market prediction by using artificial neural network. In: Proceedings of world Automation Congress (WAC), pp. 1–5. IEEE, Waikoloa, HI, USA (2014)Google Scholar
  5. 5.
    Kumar, I., Dogra, K., Utreja, K., Yadav, P.: A comparative study of supervised machine learning algorithm stock market trend prediction. In: Proceedings of 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), pp. 1003–1007. IEEE, Coimbatore (2018)Google Scholar
  6. 6.
    Loon, R.V.: Naive Bayes classifier with example simplilearn channel. Accessed 03 Aug 2019
  7. 7.
    Pedregosa, F., et al.: scikit-learn: sklearn.naive_bayes.MultinomialNB. Accessed 11 Aug 2019
  8. 8.
    Pedregosa, F., et al.: scikit-learn: learn.feature_extraction.text.TfidfVectorizer. Accessed 11 Aug 2019
  9. 9.
    Pedregosa, F., et al.: scikit-learn: machine learning in Python. Accessed 20 July 2019
  10. 10.
    Chairattanamanokorn, N., et al.: HoonSmart Breaking News. Accessed 20 Jan 2019
  11. 11.
    The Stock Exchange of Thailand.: Companies/Securities in Focus Historical Trading. Accessed 05 May 2019
  12. 12.
    Viriyayudhakorn, K.: Thai Natural Language Processing (Thai NLP) Resource. Accessed 12 Aug 2019

Copyright information

© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Knowledge Management and Knowledge Engineering Laboratory, Faculty of Information TechnologyKing Mongkut’s Institute of TechnologyBangkokThailand

Personalised recommendations