A Hybrid Model to Forecast Financial Time Series Based on Technical Analysis and Support Vector Machines

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    The aim of this paper is to find functional relations in the behaviour of the USD swaps daily level time series and, in turn, forecast future values of the series through applying a relevant machine learning technique. As our original dataset variables appeared to show strong cross correlation, we decided to use Principal Component Analysis (PCA) to process the data before passing it to our machine learning algorithm. Then, we extract some technical indicators from our historical product price time series and use them as inputs to our model. Finally, Support Vector Machines (SVMs) is applied to our processed data set to realise the forecasting, and the resulting time series can be used to generate signals of when to enter or unwind a trade. Analysis of the results demonstrates that it is advantageous to apply SVMs to forecast financial time series, based on the criteria of Root Mean Square Error (RMSE) and F-measure (F score)



  • Keywords

    Financial time series; Machine Learning; Principal Component Analysis; Support Vector Machines; USD swaps.

  • References

      [1] Cox, John C., Jonathan E. Ingersoll Jr, and Stephen A. Ross. "A theory of the term structure of interest rates." In Theory of Valuation, 2005, pp. 129-164.

      [2] Adhikari, Ratnadip, and R. K. Agrawal. "A combination of artificial neural network and random walk models for financial time series forecasting." Neural Computing and Applications 24, no. 6 (2014): 1441-1449.

      [3] Babu, C. Narendra, and B. Eswara Reddy. "A moving-average filter based hybrid ARIMA–ANN model for forecasting time series data." Applied Soft Computing 23 (2014): 27-38.

      [4] Kanchymalay, Kasturi, N. Salim, Anupong Sukprasert, Ramesh Krishnan, and Ummi Raba’ah Hashim. "Multivariate Time Series Forecasting of Crude Palm Oil Price Using Machine Learning Techniques." In IOP Conference Series: Materials Science and Engineering, vol. 226, no. 1, p. 012117. IOP Publishing, 2017.

      [5] Khashman A. and Nwulu N. I. Support Vector Machines versus Back Propagation Algorithm for Oil Price Prediction Liu D., Zhang H., Polycarpou M., Alippi C., He H. Adv. Neural Networks – ISNN 2011. ISNN 2011. Lect. Notes Comput. Sci. vol 6677. Springer, Berlin, Heidelb. 530-538

      [6] González-Mancha, Juan Javier, Juan Frausto-Solís, Guadalupe Castilla Valdez, Jesús David Terán-Villanueva, and Juan Javier González Barbosa. "Financial time series forecasting using Simulated Annealing and Support Vector Regression." International Journal of Combinatorial Optimization Problems and Informatics 8, no. 2 (2017): 10-18.

      [7] Bao, Wei, Jun Yue, and Yulei Rao. "A deep learning framework for financial time series using stacked autoencoders and long-short term memory." PloS one 12, no. 7 (2017): e0180944.

      [8] Davig, Troy, and Taeyoung Doh. "Monetary policy regime shifts and inflation persistence." Review of Economics and Statistics 96, no. 5 (2014): 862-875.

      [9] De Ketelaere, Bart, Mia Hubert, and Eric Schmitt. "Overview of PCA-based statistical process-monitoring methods for time-dependent, high-dimensional data." Journal of Quality Technology 47, no. 4 (2015): 318-335.

      [10] Shlens, Jonathon. "A tutorial on principal component analysis." arXiv preprint arXiv:1404.1100 (2014).

      [11] Ahmar, Ansari Saleh. "Sutte Indicator: A technical indicator in stock market." (2017).

      [12] Cervelló-Royo, Roberto, Francisco Guijarro, and Karolina Michniuk. "Stock market trading rule based on pattern recognition and technical analysis: Forecasting the DJIA index with intraday data." Expert systems with Applications 42, no. 14 (2015): 5963-5975.

      [13] Pring, Martin J. Martin Pring's Introduction to Technical Analysis. McGraw Hill Professional, 2015.

      [14] Chang, C. C., & Lin, C. J. (2006). Training v-support vector classifiers: theory and algorithms. Training, 13(9).

      [15] Chang, C. C., & Lin, C. J. (2011). LIBSVM: a library for support vector machines. ACM transactions on intelligent systems and technology (TIST), 2(3), 27.

      [16] Gunn, S. R. (1998). Support vector machines for classification and regression. ISIS technical report, (14), pp. 85-86.

      [17] Cristianini, N., & Shawe-Taylor, J. (2000). An introduction to support vector machines and other kernel-based learning methods. Cambridge university press.

      [18] Suykens, J. A., & Vandewalle, J. (1999). Least squares support vector machine classifiers. Neural processing letters, 9(3), 293-300.

      [19] Smits, G. F., & Jordaan, E. M. (2002). Improved SVM regression using mixtures of kernels. In Neural Networks, 2002. IJCNN'02. Proceedings of the 2002 International Joint Conference on (Vol. 3, pp. 2785-2790). IEEE.

      [20] Smola, A., & Vapnik, V. (1997). Support vector regression machines. Advances in neural information processing systems, (9), pp. 155-161.

      [21] Müller, K. R., Smola, A. J., Rätsch, G., Schölkopf, B., Kohlmorgen, J., & Vapnik, V. (1997). Predicting time series with support vector machines. In International Conference on Artificial Neural Networks. Springer Berlin Heidelberg, pp. 999-1004.

      [22] R. Darnag, E.L. M. Mazouz, A. Schmitzer, D. Villemin, A. Jarid, D. Cherqaoui, “Support vector machines: Development of QSAR models for predicting anti-HIV-1 activity of TIBO derivatives” European Journal of Medicinal Chemistry 45, p.p: 1590–1597, 2010.

      [23] Powers, D.M.W., 2011. Evaluation: from Precision, Recall and F-measure to ROC, Informedness, Markedness and Correlation. Journal of Machine Learning Technologies, 2(1), 37-63.




Article ID: 28106
DOI: 10.14419/ijet.v8i1.11.28106

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.