• DocumentCode
    3580323
  • Title

    Stock market prediction using Hidden Markov Model

  • Author

    Somani, Poonam ; Talele, Shreyas ; Sawant, Suraj

  • Author_Institution
    Dept. of Comput. Eng. & Inf. Technol., Coll. of Eng. Pune, Pune, India
  • fYear
    2014
  • Firstpage
    89
  • Lastpage
    92
  • Abstract
    Stock market is the most popular investment scheme promising high returns albeit some risks. An intelligent stock prediction model would thus be desirable. So, this paper aims at surveying recent literature in the area of Neural Network, Hidden Markov Model and Support Vector Machine used to predict the stock market fluctuation. Neural networks and SVM are identified to be the leading machine learning techniques in stock market prediction area. Also, a model for predicting stock market using HMM is presented. Traditional techniques lack in covering stock price fluctuations and so new approaches have been developed for analysis of stock price variations. Markov Model is one such recent approach promising better results. In this paper a predicting method using Hidden Markov Model is proposed to provide better accuracy and a comparison of the existing techniques is also done.
  • Keywords
    economic forecasting; hidden Markov models; investment; learning (artificial intelligence); neural nets; pricing; stock markets; support vector machines; HMM; SVM; hidden Markov model; high returns; intelligent stock prediction model; investment scheme; machine learning techniques; neural network; stock market fluctuation prediction; stock price fluctuations; stock price variations; support vector machine; Hidden Markov models; Neural networks; Prediction algorithms; Predictive models; Stock markets; Support vector machines; Testing; Hidden Markov Model; Mean Absolute Percentage Error; Mean Squared Error; Neural networks; Stock market prediction; Support Vector Machine;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Technology and Artificial Intelligence Conference (ITAIC), 2014 IEEE 7th Joint International
  • Print_ISBN
    978-1-4799-4420-0
  • Type

    conf

  • DOI
    10.1109/ITAIC.2014.7065011
  • Filename
    7065011