Abstract
In the field of quantitative finance, stock price trend prediction has always been one of the concerns of people. Stock price time series is the most important calculation basis in stock price prediction. The usual research idea is to take the one-dimensional single variable stock price time series to construct sample matrix through phase space reconstruction (PSR), and use it as the feature input of machine learning algorithm to predict the stock price. However, we often need a relatively large embedded dimension to obtain more useful information, which easily leads to the problems of high matrix dimension, over-fitting of prediction and low computational efficiency. To solve the above problems, we propose a path signature-based phase space reconstruction (PSR-PS) feature engineering approach for stock trend prediction, which can effectively extract features, reduce the dimension of high-dimensional price series data information and capture the necessary and effective information. Extensive experiments on several benchmark data sets from diverse real financial markets show that PSR-PS outperforms PSR and PSR-PCA (Principal component analysis-based PSR) in accuracy, precision and computational time, combined with different machine learning algorithms. It suggests that the proposed PSR-PS is effective.
Similar content being viewed by others
References
Packard, N.H., Crutchfield, J.P., Farmer, J.D., Shaw, R.S.: Geometry from a time series. Phys. Rev. Lett. 45(3), 712–716 (1980)
Takens, F.: Detecting strange attractors in turbulence. Lect. Notes Math. 898(2), 361–381 (1981)
Henrique, B.M., Sobreiro, V.A., Kimura, H.: Literature review: machine learning techniques applied to financial market prediction. Expert Syst. Appl. 124, 226–251 (2019)
Giamouridis, D.: Systematic investment strategies. Financ. Anal. J. 73(4), 10–14 (2017)
Chen, K.T.: Iterated path integrals. Bull. Am. Math. Soc. 2013(83), 831–879 (1977)
Yang, W., Jin, L.: The Representation and Recognition of Trajectory Data Based on Path Signature Feature and Deep Learning Methods, pp. 24–27. South China University of Technology, Guangzhou (2018)
Flint, G., Hambly, B., Lyons, T.: Discretely sampled signals and the rough Hoff process. Stoch. Process. Appl. 126(9), 2593–2614 (2016)
Tomohiro, T., Sugeno, M.: Fuzzy identification of system and its aplication to modeling and control. Trans. Syst. Man Cybern. 15(1), 116–132 (1985)
Zhang, H., Liang, J., Chai, Z.: Stock prediction based on phase space reconstruction and Echo state networks. J. Algorithms Comput. Technol. 7(1), 87–99 (2012)
Kazema, A., Sharifia, E., Hussainb, F.K., Saberic, M., Hussaind, O.K.: Support vector regression with Chaos-based firefly algorithm for stock market price forecasting. Appl. Soft Comput. 13(2), 947–958 (2013)
Zhao, S.: Integrated stock market forecasting based on phase space reconstruction and nonparametric neural network. J. Guangxi Univer. Natl. 17(3), 1158 (2018)
Chen, K.-S.: Integration of paths a faithful representation of paths by non-commutative formal power series. Trans. Am. Math. Soc. 89(2), 395–407 (1958)
Lyons, T.J.: Differential equations driven by rough signals. Revista Matematica Iberoamericana 14(2), 215–310 (1998)
Levin, D., Lyons, T., Ni, H.: Learning from the past, predicting the statistics for the future, learning an evolving system, p. 0260. arXiv preprint arXiv:1309.0260 (2013)
Xie, Z., Sun, Z., Jin, L., Ni, H., Lyons, T.: Learning spatialsemantic context with fully convolutional recurrent network for online handwritten chinese text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(8), 1903–1917 (2018)
Yang, W., Lyons, T., Ni, H., Schmid, C., Jin, L., Chang, J.: Leveraging the path signature for skeleton-based human action recognition, p. 03993. arXiv preprint arXiv:1707.03993 (2017)
Gyurko, L.G., Lyons, T., Kontkowski, M., Field, J.: Extracting information from the signature of a financial data stream. Quant. Finance 2, 10048 (2013)
Arribas, I.P., Saunders, K., Goodwin, G., Lyons, T.: A signature-based machine learning model for bipolar disorder and borderline personality disorder. Transl. Psychiatr. 2, 274 (2018)
Santoso, M., Sutjiadi, R., Lim, R.: Indonesian stock prediction using support vector machine (SVM). MATEC Web Conf. 164, 01031 (2018)
Jaiwang, G., Jeatrakul, P.: A forecast model for stock trading using support vector machine. In: International Computer Science and Engineering Conference (ICSEC) (2016)
Guo, H., Gao, B., Lu, H.: Research on stock return rate based on Boruta-PSO-SVM. Sens. Microsyst. 37(3), 51–53 (2018)
Deng, J., Li, L.: Application of parametric optimization random forests in stock forecasting. Comput. Eng. Softw. 41(01), 178–182 (2020)
Wang, S.Y., Cao, Z.F., Chen, M.Z.: Research on application of random forests in the quantitative stock selection model. Oper. Res. Manag. Sci. 25(3), 1447 (2016)
Lin, N., Qin, J.T.: Forecast of A-share stock change based on random forest. J. Univ. Shanghai Sci. Technol. 40(3), 1147 (2018)
Wang, Y., Guo, Y.K.: Application of improved XGboost model in stock forecasting. Comput. Eng. Appl. 55(20), 202–207 (2019)
Chen, J., Liu, D.X., Wu, D.S.: Stock index forecasting method based on feature selection and LSTM model. Comput. Eng. Appl. 55(6), 108–112 (2019)
Liu, S., Tang, G., Pang, B.: Rolling bearing fault diagnosis based on phase space reconstruction and stationary subspace analysis. Vib. Shock 34(22), 187–191 (2015)
Cao, L.Y.: Practical method for determining the minimum embedding dimension of a scalar time series. Physica D Nonlinear Phen. 110, 43–50 (1997)
Fathima, T.A., Jothiprakash, V.: Behavioural analysis of a time series-a Chaotic approach. Sadhana 39(3), 676–695 (2014)
Gong, Z.P.: Comparison of the calculating methods of delay time in the reconstructed phase space of manufacturing quality information system. Syst. Eng. 29(3), 81–85 (2011)
Chevyrev, I., Kormilitzin, A.: A primer on the Signature Method in Machine Learning, 03788, arXiv preprint arXiv:1603.03788 (2016)
iisignature [CP/OL]: http://www2.warwick.ac.uk/fac/cross_fac/complexity/people/students/dtc/students2013/reizenstein
Gyurko, L.G., Lyons, T.: Rough paths based numerical algorithms in computational finance, mathematics in finance. In: Santiago, C.M. and Jose L.F.P. (eds) American Mathematical Society, Real Sociedad Matematica Española, pp. 397–405 (2010)
Lyons, T., Ni, H., Levin, D.: Learning from the past, predicting the statistics of the future. Learn. Evol. Syst. 2, 1700 (2013)
Lyons, T.: Rough paths, signatures and the modelling of functions on streams. In: Proceedings of the International Congress of Mathematicians, pp. 163–184 (2014)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, C., Liu, K. Path signature-based phase space reconstruction for stock trend prediction. Int J Data Sci Anal 14, 293–304 (2022). https://doi.org/10.1007/s41060-022-00326-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41060-022-00326-z