Abstract
Most of the existing data mining approaches to time series prediction use as training data an embed of the most recent values of the time series, following the traditional linear auto-regressive methodologies. However, in many time series prediction tasks the alternative approach that uses derivative features constructed from the raw data with the help of domain theories can produce significant prediction accuracy improvements. This is particularly noticeable when the available data includes multivariate information although the aim is still the prediction of one particular time series. This latter situation occurs frequently in financial time series prediction. This paper presents a method of feature construction based on domain knowledge that uses multivariate time series information. We show that this method improves the accuracy of next-day stock quotes prediction when compared with the traditional embed of historical values extracted from the original data.
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.
Similar content being viewed by others
References
Abu-Mostafa, Y., LeBaron, B., Lo, A. and Weigend, A. (eds.): Proceedings of the Sixth International Conference on Computational Finance, CF99. MIT Press (1999)
Almeida, P. and Bento, C.: Sequential Cover Rule Induction with PA3. Proceedings of the 10th International Conference on Computing and Information (ICCI’2000), Kuwait. Springer-Verlag (2001)
Bellman, R.; Adaptative Control Processes: A Guided Tour. Princeton University Press, (1961)
Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press (1995)
Bontempi, G.: Local Learning Techniques for Modeling, Prediction and Control. Ph.D. Dissertation, Université Libre de Bruxelles, Belgium (1999)
Box, G., and Jenkins, G.: Time Series Analysis, Forecasting and Control. Holden-Day (1976)
Demark, T.: The New Science of Technical Analysis. John Wiley & Sons (1994)
Fama, E.: Efficient Capital Markets: A review of Theory and Empirical Work. Journal of Finance, 25 (1970) 383–417
Hall, M.: Correlation-Based Feature Selection for Machine Learning. Ph.D. Dissertation, Department of Computer Science, University of Waikato (1999)
Hellstrom, T.: Data Snooping in the Stock Market. Theory of Stochastic Process 5(21) (1999)
Herbst, A.: Analyzing and Forecasting Futures Prices. John Wiley & Sons (1992)
Hong, S.: Use of Contextual Information for Feature Ranking and Discretization. IEEE Transactions on Knowledge and Data Engineering, 9(5) (1997) 718–730
Hutchinson, J.: A Radial Basis Function Approach to Financial Time Series Analysis. Ph.D. Dissertation, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology (1994)
Kustrin, D.: Forecasting Financial Time series with Correlation Matrix Memories for Tactical Asset Allocation. Ph.D. Dissertation, Department of Computer Science, University of York, UK (1998)
Lawrence, S., Tsoi, A. and Giles C.: Noisy Time Series Prediction using Symbolic Representation and Recurrent Neural Network Grammatical Inference. Technical Report UMIACS-TR-96-27 and CS-TR-3625, Institute for Advanced Computer Studies, University of Maryland, MD (1996)
Michalski, R.: A Theory and Methodology of Inductive Learning. In Michalski, R., Carbonell, J., and Mitchell, T., (eds): Machine Learning: An Artificial Intelligence Approach, Vol. 1. Morgan Kaufmann (1983)
Mozer, M.: Neural Net Architectures for Temporal Sequence Processing. In: Weigend, A. and Gershenfeld, N. (eds.): Time Series Prediction: Forecasting the Future and Understanding the Past. Addison-Wesley (1994)
Murphy, J.: Technical Analysis of the Financial Markets: A Comprehensive Guide to Trading Methods and Applications. Prentice Hall (1999)
Murthy, S., Kasif, S. and Salzberg, S.: A System for Induction of Oblique Decision Trees. Journal of Artificial Intelligence Research, 2 (1994) 1–32
Povinelli, R.: Time Series Data Mining: Identifying Temporal Patterns for Characterization and Prediction of Time Series Events. Ph.D. Dissertation, Marquette University, Milwaukee, Wisconsin (1999)
Refenes, A.: Testing Strategies and Metrics. In Refenes, A. (ed.): Neural Networks in the Capital Markets. John Wiley & Sons (1995)
Sauer, T., Yorke, J. and Casdagli, M.: Embedology. Journal of Statistical Physics 65 (1991) 579–616
Scott, D.; Multivariate Density Estimation. John Wiley & Sons (1992)
Takens, F.: Detecting Strange Attractors in Turbulence. In Rand, D. and Young, L. (eds.), Lecture Notes in Mathematics, Vol. 898. Springer (1981) 366–381
Weigend, A. and Gershenfeld, N. (eds.): Time Series Prediction: Forecasting the Future and Understanding the Past. Addison-Wesley (1994)
Weigend, A., Huberman, B. and Rumelhart, D.: Predicting Sunspots and Exchange Rates with Connectionist Networks. In Casdagli, M. and Eubank, S. (eds.): Nonlinear Modeling and Forecasting, SFI Studies in the Sciences of Complexity. Addison-Wesley (1992)
Weigend, A., Zimmermann, H. and Neuneier, R.: Clearning. In Refenes, P., Abu-Mostafa, Y., Moody, J. and Weigend, A. (eds.): Neural Networks in Financial Engineering (Proceedings of NNCM’95). World Scientific (1996)
Weiss, S. and Indurkhya, N.: Predictive Data Mining: A Practical Guide. Morgan Kaufmann (1998)
Yule, G.: On a Method of Investigating Periodicities in Disturbed Series with Special Reference to Wolfer’s Sunspot Numbers. Phil. Trans. Royal Society, Series A, 226 (1927)
Yuret, D. and Maza, M.: A Genetic Algorithm System for Predicting de OEX. Technical Analysis of Stocks and Commodities, 12(6) (1994) 255–259
Zang, X. and Hutchinson, J.: Simple Architectures on Fast Machines: Practical Issues in Nonlinear Time Series Prediction. In Weigend, A. and Gershenfeld, N. (eds.): Time Series Prediction: Forecasting the Future and Understanding the Past. Addison-Wesley (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
de Almeida, P., Torgo, L. (2001). The Use of Domain Knowledge in Feature Construction for Financial Time Series Prediction. In: Brazdil, P., Jorge, A. (eds) Progress in Artificial Intelligence. EPIA 2001. Lecture Notes in Computer Science(), vol 2258. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45329-6_15
Download citation
DOI: https://doi.org/10.1007/3-540-45329-6_15
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43030-8
Online ISBN: 978-3-540-45329-1
eBook Packages: Springer Book Archive