Prediction of stock price by Hidden Markov model

Xin An

doi:10.54691/bcpbm.v38i.3709

Authors

Xin An

DOI:

https://doi.org/10.54691/bcpbm.v38i.3709

Keywords:

Hidden Markov model; Stock price forecast; EM algorithm; machine learning.

Abstract

Hidden Markov model is widely used in different fields, such as speech decoding, weather prediction, biometric, medical diagnosis and prediction. This paper explores the application of hidden Markov model in quantitative investment in the financial field, mainly in the field of securities trading. The main idea of this paper is to crack the different market states reflected in the price changes of securities. Price changes are affected by different market states at the same time, but this state is hidden and needs to be inferred. If people can calculate the relevant parameters of the state and its transition matrix, people can predict the stock price trend and establish the own trading strategy at the same time. The hidden Markov model is used as a theoretical basis in this paper, through the analysis of the fit between the stock market and the model, as well as various statistical knowledge as a tool. Through EM algorithm and machine learning as the programming basis, people finally selected Pingan and Moutai as the research objects, predicted the stock price changes through training. Therefore, when the training set is sufficiently large, hidden Markov model will have a bright performance in stock price prediction.

Downloads

Download data is not yet available.

References

Eddy S R. Profile hidden Markov models. Bioinformatics, 1998(9):755.

B Schuster‐Böckler, Bateman A. An introduction to hidden Markov models. Curr Protoc Bioinformatics, 2007.

Olivier Cappé, Moulines E, Tobias Rydén. Inference in Hidden Markov Models. Technometrics, 2006, 48(4):574-575.

Mccallum A, Freitag D, Pereira F. Maximum Entropy Markov Models for Information Extraction and Segmentation. icml, 2001.

O Cappé, Moulines E, Ryden T. Inference in Hidden Markov Models (Springer Series in Statistics). Springer-Verlag New York, Inc. 2005.

Atln B A. Speech emotion recognition using hidden Markov models. Speech Communication, 2003, 41(4):603-623.

Starner T E. Visual Recognition of American Sign Language Using Hidden Markov Model. 1995.

Rabiner L R, Juang B H. Hidden Markov Models for Speech Recognition — Strengths and Limitations. Springer Berlin Heidelberg, 1992.

Nielsen H, Krogh A. Prediction of signal peptides and signal anchors by a hidden Markov model. Intelligent Systems for Molecular Biology, 1998, 6:122-130.

Karplus K, Barrett C, Hughey R. Hidden Markov models for detecting remote protein homologies. Bioinformatics, 1998(10):846-856.

Jarrow R A, Lando D, Turnbull S M. A Markov Model for the Term Structure of Credit Risk Spreads. Review of Financial Studies, 2004, 10(2):481-523.