Simultaneous pursuit of out-of-sample performance and sparsity in index tracking portfolios

Index tracking is a passive investment strategy in which a fund (e.g., an ETF: exchange traded fund) manager purchases a set of assets to mimic a market index. The tracking error, i.e., the difference between the performances of the index and the portfolio, may be minimized by buying all the assets contained in the index. However, this strategy results in a considerable transaction cost and, accordingly, decreases the return of the constructed portfolio. On the other hand, a portfolio with a small cardinality may result in poor out-of-sample performance. Of interest is, thus, constructing a portfolio with good out-of-sample performance, while keeping the number of assets invested in small (i.e., sparse). In this paper, we develop a tracking portfolio model that addresses the above conflicting requirements by using a combination of L0- and L2-norms. The L2-norm regularizes the overdetermined system to impose smoothness (and hence has better out-of-sample performance), and it shrinks the solution to an equally-weighted dense portfolio. On the other hand, the L0-norm imposes a cardinality constraint that achieves sparsity (and hence a lower transaction cost). We propose a heuristic method for estimating portfolio weights, which combines a greedy search with an analytical formula embedded in it. We demonstrate that the resulting sparse portfolio has good tracking and generalization performance on historic data of weekly and monthly returns on the Nikkei 225 index and its constituent companies.

[1]  Raman Uppal,et al.  Improving Performance By Constraining Portfolio Norms: A Generalized Approach to Portfolio Optimization , 2007 .

[2]  Tong Zhang,et al.  Adaptive Forward-Backward Greedy Algorithm for Sparse Learning with Linear Models , 2008, NIPS.

[3]  R. Roll,et al.  A Mean/Variance Analysis of Tracking Error , 1992 .

[4]  Akiko Takeda,et al.  Support vector regression as conditional value-at-risk minimization with application to financial time-series analysis , 2010, 2010 IEEE International Workshop on Machine Learning for Signal Processing.

[5]  Peter Winker,et al.  Robust portfolio optimization with a hybrid heuristic algorithm , 2012, Comput. Manag. Sci..

[6]  Bernhard Schölkopf,et al.  New Support Vector Algorithms , 2000, Neural Computation.

[7]  Christian M. Hafner,et al.  Ridge regression revisited , 2005 .

[8]  I. Daubechies,et al.  Sparse and stable Markowitz portfolios , 2007, Proceedings of the National Academy of Sciences.

[9]  Hiroshi Konno,et al.  Portfolio optimization under D.C. transaction costs and minimal transaction unit constraints , 2002, J. Glob. Optim..

[10]  Klaus Nordhausen,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition by Trevor Hastie, Robert Tibshirani, Jerome Friedman , 2009 .

[11]  Jean-Luc Prigent,et al.  Portfolio Optimization and Performance Analysis , 2007 .

[12]  Victor DeMiguel,et al.  Optimal Versus Naive Diversification: How Inefficient is the 1/N Portfolio Strategy? , 2009 .

[13]  Alberto Suárez,et al.  A hybrid optimization approach to index tracking , 2009, Ann. Oper. Res..

[14]  R. Tibshirani,et al.  Regression shrinkage and selection via the lasso: a retrospective , 2011 .

[15]  A. E. Hoerl,et al.  Ridge regression: biased estimation for nonorthogonal problems , 2000 .

[16]  Abhimanyu Das,et al.  Algorithms for subset selection in linear regression , 2008, STOC.

[17]  H. Zimmermann,et al.  A linear model for tracking error minimization , 1999 .

[18]  Zhifeng Zhang,et al.  Adaptive time-frequency decompositions with matching pursuit , 1994, Defense, Security, and Sensing.

[19]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[20]  Yazid M. Sharaiha,et al.  Heuristics for cardinality constrained portfolio optimisation , 2000, Comput. Oper. Res..

[21]  Panos M. Pardalos,et al.  Financial Engineering, E-commerce and Supply Chain , 2010 .

[22]  Honggang Xue,et al.  Sparse Index Tracking : An L 1 / 2 Regularization Based Model and Solution , 2011 .

[23]  Stephen P. Boyd,et al.  Portfolio optimization with linear and fixed transaction costs , 2007, Ann. Oper. Res..

[24]  Hiroshi Konno,et al.  Portfolio optimization problem under concave transaction costs and minimal transaction unit constraints , 2001, Math. Program..

[25]  Michel Minoux,et al.  Accelerated greedy algorithms for maximizing submodular set functions , 1978 .

[26]  Raman Uppal,et al.  A Generalized Approach to Portfolio Optimization: Improving Performance by Constraining Portfolio Norms , 2009, Manag. Sci..

[27]  Manfred Gilli,et al.  The Threshold Accepting Heuristic for Index Tracking , 2001 .

[28]  Zhifeng Zhang,et al.  Adaptive time-frequency decompositions , 1994 .

[29]  Y. C. Pati,et al.  Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[30]  Tso-Jung Yen,et al.  Solving Norm Constrained Portfolio Optimization via Coordinate-Wise Descent Algorithms , 2010, Comput. Stat. Data Anal..

[31]  M. L. Fisher,et al.  An analysis of approximations for maximizing submodular set functions—I , 1978, Math. Program..

[32]  C. Lucas,et al.  Heuristic algorithms for the cardinality constrained efficient frontier , 2011, Eur. J. Oper. Res..

[33]  Akiko Takeda,et al.  On the role of norm constraints in portfolio selection , 2011, Comput. Manag. Sci..

[34]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[35]  Abhimanyu Das,et al.  Submodular meets Spectral: Greedy Algorithms for Subset Selection, Sparse Approximation and Dictionary Selection , 2011, ICML.

[36]  D. Ruppert The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .