Predicting stock price of construction corporates using optimized machine learning regression sliding-window

Abstract: 162 | PDF: 59

##plugins.themes.academic_pro.article.main##

Author

  • Kha Thi Nguyen, Thi Phuong Trang Pham

Keywords:

Stock market prices
sliding-window
machine learning
firefly algorithm
least squares support vector regression
time series

Abstract

Forecasting changes in stock market prices plays a critical role in the development of company. However, predicting stock prices is a difficult problem because of the complexity of the stock market data. Therefore, the objective of this paper is to propose an optimized machine learning regression sliding-window model for forecasting stock prices for construction companies. The proposed model integrates the firefly algorithm (FA) and the least squares support vector regression (LSSVR). The FA automatically fine-tunes the hyper-parameters of the LSSVR to construct an optimized LSSVR model. The developed model is called the FA-LSSVM. This investigation uses stock datasets of construction companies in Taiwan; namely 2545.TW, 2597.TW and 5534.TW to verify the effectiveness of the proposed model. The results reveal that for 2597.TW stock price dataset, the FA-LSSVM model obtains highest performance with a root mean square error (RMSE) of 1.548, a mean absolute error (MAE) of 0.617, a mean absolute percentage error (MAPE) of 1.372%, and a mean square error (MSE) of 2.396. Therefore, the proposed model is a promising predicting technique for non-linear time series.

References

    [1] K.K. Oh KJ, Analyzing stock market tick data using piecewise nonlinear model, Expert Systems with Application, 22 (2002) 249-55.
    [2] W. Leigh, M. Paz, R. Purvis, An analysis of a hybrid neural network and pattern recognition technique for predicting short-term increases in the NYSE composite index, Omega 30(2) (2002) 69-76.
    [3] S.-Y. Lin, C.-H. Chen, C.-C. Lo, Currency Exchange Rates Prediction based on Linear Regression Analysis Using Cloud Computing, International Journal of Grid and Distributed Computing 6 (2013) 10.
    [4] A. Abdoos, M. Hemmati, A.A. Abdoos, Short term load forecasting using a hybrid intelligent method, Knowledge-Based Systems 76 (2015) 139-147.
    [5] V.N. Vapnik, The nature of statistical learning theory, Springer-Verlag New York, Inc.1995.
    [6] J.-S. Chou, A.-D. Pham, Nature-inspired metaheuristic optimization in least squares support vector regression for obtaining bridge scour information, Information Sciences 399 (2017) 64-80.
    [7] T. Xiong, Y. Bao, Z. Hu, Multiple-output support vector regression with a firefly algorithm for interval-valued stock price index forecasting, Knowledge-Based Systems 55 (2014) 87-100.
    [8] A.K. Rout, R. Bisoi, P.K. Dash, A low complexity evolutionary computationally efficient recurrent Functional link Neural Network for time series forecasting, IEEE Power, Communication and Information Technology Conference, PCITC 2015, Institute of Electrical and Electronics Engineers Inc., Bhubaneswar, India, 2015, pp. 576-582.
    [9] S.K. Pal, Rai, C. S., and Singh, A. P., Comparative study of firefly algorithm and particle swarm optimization for noisy non-linear optimization problems., (2012) Int. J. Intell. Syst. Appl., 4(10), 50–57.
    [10] J. Olamaei, M. Moradi, T. Kaboodi, A new adaptive modified Firefly Algorithm to solve optimal capacitor placement problem, Electrical Power Distribution Networks (EPDC), 2013 18th Conference on, 2013, pp. 1-6.
    [11] N.-D. Hoang, A.-D. Pham, a.M.-T. Cao, A Novel Time Series Prediction Approach Based on a Hybridization of Least Squares Support Vector Regression and Swarm Intelligence, Applied Computational Intelligence and Soft Computing (2014) 8.
    [12] J.A.K. Suykens, T.V. Gestel, J.D. Brabanter, B.D. Moor, J. Vandewalle, Least squares support vector machines, World Scientific, Singapore 2002.
    [13] X.-S. Yang, Nature-Inspired Metaheuristic Algorithms, Luniver Press 2008.
    [14] S. Łukasik, S. Żak, Firefly Algorithm for Continuous Constrained Optimization Tasks, in: N.T. Nguyen, R. Kowalczyk, S.-M. Chen (Eds.), Computational Collective Intelligence. Semantic Web, Social Networks and Multiagent Systems: First International Conference, ICCCI 2009, Wrocław, Poland, October 5-7, 2009. Proceedings, Springer Berlin Heidelberg, Berlin, Heidelberg, 2009, pp. 97-106.
    [15] E. Hadavandi, H. Shavandi, A. Ghanbari, Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting, Knowledge-Based Systems 23(8) (2010) 800-808.
    [16] M. Göçken, M. Özçalıcı, A. Boru, A.T. Dosdoğru, Integrating metaheuristics and Artificial Neural Networks for improved stock price prediction, Expert Systems with Applications 44 (2016) 320-331.
    [17] C.M. Anish, B. Majhi, Hybrid nonlinear adaptive scheme for stock market prediction using feedback FLANN and factor analysis, Journal of the Korean Statistical Society 45(1) (2016) 64-76.
    [18] R. Dash, P. Dash, Efficient stock price prediction using a Self Evolving Recurrent Neuro-Fuzzy Inference System optimized through a Modified Differential Harmony Search Technique, Expert Systems with Applications 52 (2016) 75-90.
    [19] D. Bhattacharya, A. Konar, P. Das, Secondary factor induced stock index time-series prediction using Self-Adaptive Interval Type-2 Fuzzy Sets, Neurocomputing 171 (2016) 551-568.
    [20] Shunrong Shen, Haomiao Jiang, T. Zhang, Stock Market Forecasting Using Machine Learning Algorithms, IEEE Transactions on Neural Networks 84(4) (2015) 21.
Read more

##plugins.themes.academic_pro.article.sidebar##

Published

Nov 30, 2017
Download
PDF
How to Cite
Kha Thi Nguyen, Thi Phuong Trang Pham. “Predicting Stock Price of Construction Corporates Using Optimized Machine Learning Regression Sliding-Window”. The University of Danang - Journal of Science and Technology, vol. 11, no. 120.4, Nov. 2017, pp. 87-89, https://jst-ud.vn/jst-ud/article/view/3746.

##plugins.themes.academic_pro.article.details##