Abstract
Accurate prediction of financial time series or their direction of changes may result in highly profitable returns. There are many approaches to build such models. One of them is to apply machine learning algorithms i.e. Neural Networks or Support Vector Machines. In this paper we would like to propose a modified version of Support Vector Machine classifier, Volume Weighted Support Vector Machine which has the ability to predict short term trends on the stock market. Modification is based on the assumption that incorporating transaction volume into penalty function may lead to better future trends forecasting. Experimental results obtained on the data set composed of daily quotations from 420 stocks from S&P500 Index showed that proposed method gives statistically better results than basic algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ładyżyński, P., Żbikowski, K., Grzegorzewski, P.: Stock Trading with Random Forests, Trend Detection Tests and Force Index Volume Indicators. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013, Part II. LNCS, vol. 7895, pp. 441–452. Springer, Heidelberg (2013)
Chen, S., Dai, Q.: Discounted least squares-improved circular back-propogation neural networks with applications in time series prediction. Neural Computing and Applications 14(3), 250–255 (2005), http://link.springer.com/10.1007/s00521-004-0461-9
Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning 20(3), 273–297 (1995)
Lai, R.K., Fan, C.Y., Huang, W.H., Chang, P.C.: Evolving and clustering fuzzy decision tree for financial time series data forecasting. Expert Systems with Applications 36(2), 3761–3773 (2009), http://linkinghub.elsevier.com/retrieve/pii/S0957417408001474
Momot, A., Momot, M.: Perspektywy zastosowań metod statystycznych w konstrukcji strategii działania na rynkach kapitałowych – wykorzystanie systemów hierarchicznych oraz regularyzacji. Studia Informatica 34(2A), 263–274 (2013)
Murphy, J.J.: Technical Analysis of the Financial Markets. New York Institute of Finance (1999)
Platt, J.C.: Fast Training of Support Vector Machines Using Sequential Minimal Optimization. In: Advances in Kernel Methods, pp. 185–208. MIT Press (1999)
Tay, F.E.H., Cao, L.J.: Modified support vector machines in financial time series forecasting. Neurocomputing 48, 847–861 (2002)
Tay, F.E.H., Cao, L.: Application of support vector machines in financial time series forecasting. Omega 29, 309–317 (2001)
Vapnik, V., Chervonenkis, A.J.: On The Uniform Convergence of Relative Frequencies of Events to their Probabilities. Theory of Probability and its Applications 16(2), 264–280 (1971)
Welch, B.L.: The generalization of “student’s” problem when several different population variances are involved. Biometrika 34, 28–35 (1947)
Yu, H., Kim, S.: SVM Tutorial – Classification, Regression and Ranking. In: Rozenberg, G., Bäck, T., Kok, J.N. (eds.) Handbook of Natural Computing, pp. 479–506. Springer, Heidelberg (2012), http://link.springer.com/10.1007/978-3-540-92910-9
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Żbikowski, K. (2014). Time Series Forecasting with Volume Weighted Support Vector Machines. In: Kozielski, S., Mrozek, D., Kasprowski, P., Małysiak-Mrozek, B., Kostrzewa, D. (eds) Beyond Databases, Architectures, and Structures. BDAS 2014. Communications in Computer and Information Science, vol 424. Springer, Cham. https://doi.org/10.1007/978-3-319-06932-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-319-06932-6_24
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-06931-9
Online ISBN: 978-3-319-06932-6
eBook Packages: Computer ScienceComputer Science (R0)