An improvement of hidden Markov model for stock market predictions

被引：0
作者：
Chavoshi S.K. [1 ]
Mansouri A. [2 ]
Sheidani S. [1 ]
机构：
[1] Department of Business, Faculty of Management, Kharazmi University, Tehran
[2] Department of Engineering, Faculty of Computer Engineering, Kharazmi University, Tehran
来源：
International Journal of Reasoning-based Intelligent Systems | 2022年 / 14卷 / 2-3期
关键词：
autoregressive; hidden Markov models; open orders; settled transactions; TEDPIX;
D O I：
10.1504/IJRIS.2022.125433
中图分类号：
学科分类号：
摘要：
This paper predicts Tehran Exchange Dividend and Price Index (TEDPIX) by finding a pattern in TEDPIX through settled transactions and open orders volume effects. To do so, we improve an autoregressive hidden Markov model (AR-HMM) by adding a more hidden layer. Then, we utilised a genetic algorithm for long term daily trend predictions. By exploiting the obtained information of predicted five days using the genetic algorithm, we update the parameters of improved AR-HMM. This stepwise prediction-updating process continues until all desired number of future days stock exchange indices get predicted. Comparing our new scheme with other studied Markov family models shows that the added features lead to achieve more accuracy and less prediction errors. Experimental results show that mean absolute percentage error of all predictions by our improved AR-HMM approach are less than 5% which indicates far better performance of our method against Markov and Hidden Markov Models. Copyright © 2022 Inderscience Enterprises Ltd.
引用
收藏
页码：144 / 153
页数：9
相关论文
共 49 条
  • [1] Alpaydin E., Introduction to Machine Learning, (2014)
  • [2] Bengio Y., LeCun Y., Nohl C., Burges C., LeRec: a NN/HMM hybrid for on-line handwriting recognition, Neural Computation, 7, 6, pp. 1289-1303, (1995)
  • [3] Bonde G., Khaled R., Stock Price Prediction using Genetic Algorithms and Evolution Strategies, (2010)
  • [4] Caetano D.S., O'Meara B.C., Beaulieu J.M., Hidden state models improve state-dependent diversification approaches, including biogeographical models, Evolution, 72, 11, pp. 2308-2324, (2018)
  • [5] Cao Y., Li Y., Coleman S., Belatreche A., McGinnity T.M., A hidden Markov model with abnormal states for detecting stock price manipulation, the 2013 IEEE International Conference on Systems, Man, and Cybernetics, (2013)
  • [6] De Angelis L., Paas L.J., A dynamic analysis of stock markets using a hidden Markov model, Journal of Applied Statistics, 40, 8, pp. 1682-1700, (2013)
  • [7] Esfahanipour A., Mousavi S., Genetic programming application to generate technical trading rules in stock markets, International Journal of Reasoning-based Intelligent Systems, 2, (2010)
  • [8] Fang Z., George K., Application of machine learning: an analysis of Asian options pricing using neural network, the 2017 IEEE 14th International Conference on e-Business Engineering (ICEBE), (2017)
  • [9] Gandhmal D.P., Kumar K., Systematic analysis and review of stock market prediction techniques, Computer Science Review, 34, (2019)
  • [10] Gupta A., Dhingra B., Stock market prediction using hidden Markov models, the 2012 Students Conference on Engineering and Systems (SCES), (2012)
12345