Regular PapersNo Access

PORTFOLIO SELECTION AND ONLINE LEARNING

TATSIANA LEVINA

School of Business, Queen's University, 143 Union Street, Kingston, Ontario K7L 3N6, Canada

Search for more papers by this author

and

GLENN SHAFER

School of Business, Rutgers University, 180 University Avenue 07102, Newark, New Jersey 07102, USA

Search for more papers by this author

https://doi.org/10.1142/S0218488508005364Cited by:10 (Source: Crossref)

Abstract

This paper studies a new strategy for selecting portfolios in the stock market. The strategy is inspired by two streams of previous work: (1) work on universalization of strategies for portfolio selection, which began with Thomas Cover's work on constant rebalanced portfolios, published in 1991,⁴ and (2) more general work on universalization of online algorithms,^17,21,23,30 especially Vladimir Vovk's work on the aggregating algorithm and Markov switching strategies.³² The proposed investment strategy achieves asymptotically the same exponential rate of growth as the portfolio that turns out to be best expost in the long run and does not require any underlying statistical assumptions on the nature of the stock market.

Keywords:

References

K. Akcoglu, P. Drineas and M.-Y. Kao, Fast universalization of investment strategies with provably good relative returns, Int. Colloquium on Automata, Languages and Programming (ICALP) (2002) pp. 888–900. Google Scholar
P. Algoet and T. M. Cover, Annals of Probability 16, 876 (1988), DOI: 10.1214/aop/1176991793. Crossref, Web of Science, Google Scholar
A. Agarwalet al., Algorithms for portfolio man agement based on the Newton method, Proc. 23rd Int. Conf. Machine Learning (ICML '06) (2006) pp. 9–16. Google Scholar
A. Blum and A. Kalai, Machine Learning 30(1), 23 (1998), DOI: 10.1023/A:1007402410823. Crossref, Web of Science, Google Scholar
A. Borodin and R. El-Yaniv , Online Computation and Competitive Analysis ( Cambridge University Press , New York , 1998 ) . Google Scholar
A. Borodin, R. El-Yaniv and V. Gogan, Latin American Theoretical Informatics 173 (2000), DOI: 10.1007/10719839_19. Google Scholar
A. Borodin, R. El-Yaniv and V. Gogan, J. Artificial Intelligence Research 21, 579 (2004). Crossref, Web of Science, Google Scholar
O. Bousquet and M. K. Warmuth, Journal of Machine Learning Research (2001). Google Scholar
N. Cesa-Bienachiet al., J. Association for Computing Machinery 44, 427 (1997). Crossref, Web of Science, Google Scholar
N. Cesa-Bienachi and G. Lugosi , Prediction, Learning, and Games ( Cambridge University Press , New York , 2006 ) . Crossref, Google Scholar
T. M. Cover, Mathematical Finance 1, 1 (1991), DOI: 10.1111/j.1467-9965.1991.tb00002.x. Crossref, Google Scholar
T. M. Cover and E. Ordentlich, IEEE Transactions on Information Theory 42(2), 348 (1996), DOI: 10.1109/18.485708. Crossref, Web of Science, Google Scholar
J. E. Cross and A. R. Barron, Mathematical Finance 13(2), 245 (2003), DOI: 10.1111/1467-9965.00016. Crossref, Web of Science, Google Scholar
L. Györfi, G. Lugosi and F. Udina, Mathematical Finance (2005). Google Scholar
D. Helmboldet al., Mathematical Finance 8(4), 325 (1998), DOI: 10.1111/1467-9965.00058. Crossref, Web of Science, Google Scholar
M. Herbster and M. K. Warmuth, Tracking the best expert, Proc. Twelfth Int. Conf. on Machine Learning (1995) pp. 286–294. Google Scholar
M. Herbster and M. K. Warmuth, J. Machine Learning 32, 151 (1998), DOI: 10.1023/A:1007424614876. Crossref, Web of Science, Google Scholar
G. Iyengar, Mathematical Finance 15(2), 359 (2005), DOI: 10.1111/j.0960-1627.2005.00223.x. Crossref, Web of Science, Google Scholar
A. Kalai and S. Vempala , Efficient algorithms for universal portfolios , Proc. 41st Annual Symp. on Foundations of Computer Science (FOCS '00) ( 2000 ) . Google Scholar
J. Kelly, Bell System Technical Journal 35, 917 (1956). Crossref, Web of Science, Google Scholar
J. Kivinen and M. K. Warmuth, Information and Computation 132(1), 1 (1997), DOI: 10.1006/inco.1996.2612. Crossref, Web of Science, Google Scholar
T. Levina, Using the aggregating algorithm for portfolio selection, Ph.D. Theses, 2004 . Google Scholar
N. Littlestone and M. K. Warmuth, Information and Computation 108, 212 (1994), DOI: 10.1006/inco.1994.1009. Crossref, Web of Science, Google Scholar
D. MacKay , Information Theory, Inference, and Learning Algorithms ( Cambridge University Press , 2003 ) . Google Scholar
M. O'Hara , Market Microstructure Theory ( Blackwell , Massachusetts , 1997 ) . Google Scholar
E. Platen, Australian Economic Papers (2005). Google Scholar
C. Robert and G. Casella , Monte Carlo Statistical Methods ( Springer-Verlag , 1999 ) . Crossref, Google Scholar
Y. Singer, Int. J. Neural Systems 8(4), 445 (1998), DOI: 10.1142/S0129065797000434. Link, Web of Science, Google Scholar
Y. Singer, Switching portfolios, Proc. 14th Conf. on Uncertainty in Artificial Intelligence (UAI '98) (1998) pp. 485–495. Google Scholar
V. Vovk, Aggregating strategies, Proc. Third Annual Workshop on Computational Learning Theory (Morgan Kaufmann, San Mateo, CA, 1990) pp. 371–383. Google Scholar
V. Vovk, Derandomizing stochastic prediction strategies, Proc. 10th Annual Conf. on Computational Learning Theory (1997) pp. 32–42. Google Scholar
V. Vovk, Machine Learning 35, 247 (1999), DOI: 10.1023/A:1007595032382. Crossref, Web of Science, Google Scholar
V. Vovk and C. Watkins, Universal portfolio selection, Proc. Eleventh Annual Conf. on Computational Learning Theory (ACM Press, 1998) pp. 12–23. Google Scholar