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
  • [21] Lajos J., George K., Park N., A six state HMM for the S&P 500 stock market index, the Proceedings of the International Conference on Modeling, Simulation and Visualization Methods (MSV), (2011)
  • [22] Langrock R., MacDonald I.L., Zucchini W., Some nonstandard stochastic volatility models and their estimation using structured hidden Markov models, Journal of Empirical Finance, 19, 1, pp. 147-161, (2012)
  • [23] Mahmoud S., Recognition of writer-independent off-line handwritten Arabic (Indian) numerals using hidden Markov models, Signal Processing, 88, 4, pp. 844-857, (2008)
  • [24] Mandziuk J., Jaruszewicz M., Neuro-genetic system for stock index prediction, Journal of Intelligent and Fuzzy Systems, 22, 2–3, pp. 93-123, (2011)
  • [25] McClintock B.T., Michelot T., momentuHMM: R package for generalized hidden Markov models of animal movement, Methods in Ecology and Evolution, 9, 6, pp. 1518-1530, (2018)
  • [26] Mehrabanpoor M., Bahador B.V., Jandaghi G., Stock exchange indices and turnover value-evidence from Tehran Stock Exchange, African Journal of Business Management, 5, 3, pp. 783-791, (2011)
  • [27] Mitilineos S.A., Artikis P.G., Forecasting of future stock prices using neural networks and genetic algorithms, International Journal of Decision Sciences, Risk and Management, 7, (2017)
  • [28] Mohtashami A., Alinezhad A., Designing a green supply chain network using LCA method: a robust optimisation approach, International Journal of Logistics Systems and Management, 31, 2, pp. 207-223, (2018)
  • [29] Monjazeb M., Gohari H.H., Impact of oil exports income on tehran stock exchange dividend and price index (TEDPIX), model selection, World Applied Sciences Journal, 22, 6, pp. 819-823, (2013)
  • [30] Naik R.L., Ramesh D., Manjula B., Govardhan A., Prediction of stock market index using genetic algorithm, Computer Engineering and Intelligent Systems, 3, 7, pp. 162-171, (2012)
12345