Internal Regret in On-Line Portfolio Selection

This paper extends the game-theoretic notion of internal regret to the case of on-line potfolio selection problems. New sequential investment strategies are designed to minimize the cumulative internal regret for all possible market behaviors. Some of the introduced strategies, apart from achieving a small internal regret, achieve an accumulated wealth almost as large as that of the best constantly rebalanced portfolio. It is argued that the low-internal-regret property is related to stability and experiments on real stock exchange data demonstrate that the new strategies achieve better returns compared to some known algorithms.

[1]  D. Blackwell.  An analog of the minimax theorem for vector payoffs. , 1956 .

[2]  James Hannan,et al.  4. APPROXIMATION TO RAYES RISK IN REPEATED PLAY , 1958 .

[3]  Thomas M. Cover,et al.  An algorithm for maximizing expected log investment return , 1984, IEEE Trans. Inf. Theory.

[4]  Neil D. Pearson,et al.  Consumption and Portfolio Policies With Incomplete Markets and Short‐Sale Constraints: the Finite‐Dimensional Case , 1991 .

[5]  D. Fudenberg,et al.  Consistency and Cautious Fictitious Play , 1995 .

[6]  Erik Ordentlich,et al.  Universal portfolios with side information , 1996, IEEE Trans. Inf. Theory.

[7]  T. Cover.  Universal Portfolios , 1996 .

[8]  Yoram Singer,et al.  On‐Line Portfolio Selection Using Multiplicative Updates , 1998, ICML.

[9]  Manfred K. Warmuth,et al.  How to use expert advice , 1997, JACM.

[10]  A. Blum,et al.  Universal portfolios with and without transaction costs , 1997, COLT '97.

[11]  S. Hart,et al.  A simple adaptive procedure leading to correlated equilibrium , 2000 .

[12]  Víctor Dalmau,et al.  A Dichotomy Theorem for Learning Quantified Boolean Formulas , 1997, COLT.

[13]  Yoram Singer,et al.  Switching Portfolios , 1998, Int. J. Neural Syst..

[14]  Erik Ordentlich,et al.  The Cost of Achieving the Best Portfolio in Hindsight , 1998, Math. Oper. Res..

[15]  G. Lugosi,et al.  On Prediction of Individual Sequences , 1998 .

[16]  G. Lugosi,et al.  On Prediction of Individual Sequences , 1998 .

[17]  D. Fudenberg,et al.  Conditional Universal Consistency , 1999 .

[18]  BlumAvrim,et al.  Universal Portfolios With and Without Transaction Costs , 1999 .

[19]  S. Hart,et al.  A General Class of Adaptive Strategies , 1999 .

[20]  Dean P. Foster,et al.  Regret in the On-Line Decision Problem , 1999 .

[21]  Allan Borodin,et al.  On the Competitive Theory and Practice of Portfolio Selection (Extended Abstract) , 2000, LATIN.

[22]  Claudio Gentile,et al.  Adaptive and Self-Confident On-Line Learning Algorithms , 2000, J. Comput. Syst. Sci..

[23]  Amy Greenwald,et al.  A General Class of No-Regret Learning Algorithms and Game-Theoretic Equilibria , 2003, COLT.

[24]  Nicolò Cesa-Bianchi,et al.  Potential-Based Algorithms in On-Line Prediction and Game Theory , 2003, Machine Learning.

[25]  Yishay Mansour,et al.  From External to Internal Regret , 2005, J. Mach. Learn. Res..

[26]  Gábor Lugosi,et al.  Learning correlated equilibria in games with compact sets of strategies , 2007, Games Econ. Behav..