Abstract
Passive aggressive algorithms for online portfolio selection are recently shown empirically to achieve state-of-the-art performance in various stock markets. PAMR, one of online portfolio selections, is based on passive aggressive algorithms with an insensitive loss function. Inspired by the mean reversion property and the momentum property of financial markets, we present a passive aggressive algorithm by introducing a piecewise loss function and achieve a novel online portfolio selection strategy named “Passive Aggressive Combined Strategy” (PACS). PACS is able to effectively exploit the power of price reversal and price momentum for online portfolio selection. From our empirical results, we find that PACS can overcome the drawbacks of existing mean reversion algorithms or momentum algorithms and achieve significantly better results. In addition to superior performance, PACS also runs extremely fast and thus is very suitable for real-life large-scale applications.
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
Borodin, A., El-Yaniv, R., Gogan, V.: Can We Learn to Beat the Best Stock. Journal of Artificial Intelligence Research 21, 579–594 (2004)
Li, B., Hoi, S.C.H.: On-Line Portfolio Selection with Moving Average Rever-sion. In: Proceedings of the 29th International Conference on Machine Learning, vol. 1, pp. 273–228. Omnipress, Madison (2012)
Li, B., Hoi, S.C.H., Zhao, P., Gopalkrishnan, V.: Confidence weighted mean reversion strategy for on-line portfolio selection. ACM Transactions on Knowledge Discovery from Data 9(4), 1–34 (2012)
Li, B., Zhao, P., Hoi, S.C.H., Gopalkrishnan, V.: Passive aggressive mean re-version strategy for portfolio selection. Machine Learning 87(2), 221–258 (2012)
Kalai, A., Vempala, S.: Efficient Algorithms for Universal Portfolios. Journal of Machine Learning research 3(3), 423–440 (2003)
Gao, L., Zhang, W.G.: Online portfolio selection using ant colony. In: The 2nd IEEE International Conference on Management and Electronic Information, vol. 3, pp. 71–73. IEEE Press, New York (2012)
Gao, L., Zhang, W.G.: On-line portfolio selection via mean reversion strategy. Journal of Theoretical and Applied Information Technology 45(1), 136–143 (2012)
Gao, L., Zhang, W.G.: Combined mean reversion strategy for on-line portfolio selection. International Journal of Applied Mathematics and Statistics 45(15), 14:349–14:355 (2013)
Gao, L., Zhang, W.G.: Weighted moving average passive aggressive algorithm for online portfolio. In: Fifth International Conference on Intelligence Human-Machine Systems and Cybernetics, vol. 1, pp. 327–330. IEEE Press, New York (2013)
Cover, T.M.: Universal portfolio. Mathematics Finance 1(1), 1–29 (1991)
Cover, T.M.: Universal data compression and portfolio selection. In: Proceedings of the 37th IEEE Symposium on Foundations of Computer Science, pp. 534–538. IEEE Press, Los Alamitos (1996)
Iyengar, G.: Universal investment in markets with transaction costs. Mathematical Finance 15(2), 359–371 (2005)
Fagiuoli, E., Stella, F., Ventura, A.: Constant rebalanced portfolios and side-information. Quantitative Finance 7(2), 161–173 (2007)
Helmbold, D.P., Schapire, R.E., Singer, Y., Warmuth, M.K.: On-line port-folio selection using multiplicative updates. Mathematical Finance 8(4), 325–347 (1998)
Singer, Y.: Switching portfolios. International Journal of Neural Systems 8(4), 488–495 (1997)
Kelly Jr., J.L.: A new interpretation of information rate. Bell Systems Technical Journal 35(4), 917–926 (1956)
Jarrow, R.A., Maksimovic, V., Ziemba, W.T.: Capital Growth Theory. In: Finance Handbook in OR & MS, vol. 9, pp. 123–144 (1995)
Jegadeesh, N.: Evidence of predictable behavior of security returns. Journal of Finance 45(3), 881–898 (1990)
Wu, Y.R.: Momentum Trading, Mean Reversal and Over reaction in Chinese Stock Market. Review of Quantitative Finance and Accounting 37, 301–323 (2011)
Crammer, K., Dekel, O., Keshet, S., Shalev-Shwartz, S., Singer, Y.: Online passive-aggressive algorithms. Journal of Machine Learning Research 7, 551–585 (2006)
Boyd, S., Vandenberghe, L.: Convex optimization. Cambridge University Press, New York (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gao, L., Zhang, W., Tang, Q. (2013). Passive Aggressive Algorithm for Online Portfolio Selection with Piecewise Loss Function. In: Motoda, H., Wu, Z., Cao, L., Zaiane, O., Yao, M., Wang, W. (eds) Advanced Data Mining and Applications. ADMA 2013. Lecture Notes in Computer Science(), vol 8347. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-53917-6_32
Download citation
DOI: https://doi.org/10.1007/978-3-642-53917-6_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-53916-9
Online ISBN: 978-3-642-53917-6
eBook Packages: Computer ScienceComputer Science (R0)