Abstract
Portfolio optimization approaches inevitably rely on multivariate modeling of markets and the economy. In this paper, we address three sources of error related to the modeling of these complex systems: 1. oversimplifying hypothesis; 2. uncertainties resulting from parameters’ sampling error; 3. intrinsic non-stationarity of these systems. For what concerns point 1. we propose a \(L_0\)-norm sparse elliptical modeling and show thatsparsification is effective. We quantify the effects of points 2. and 3. by studying the models’ likelihood in- and out-of-sample for parameters estimated over different train windows. We show that models with larger off-sample likelihoods lead to better performing portfolios only for shorter train sets. For larger train sets, we found that portfolio performances deteriorate and detaches from the models’ likelihood, highlighting the role of non-stationarity. Investigating the out-of-sample likelihood of individual observations we show that the system changes significantly through time. Larger estimation windows lead to stable likelihood in the long run, but at the cost of lower likelihood in the short term: the “optimal” fit in finance needs to be defined in terms of the holding period. Lastly, we show that sparse models outperform full-models and conventional GARCH extensions by delivering higher out of sample likelihood, lower realized volatility and improved stability, avoiding typical pitfalls of conventional portfolio optimization approaches.
Similar content being viewed by others
References
Alexander, C., and A. Chibumba. 1997. Multivariate orthogonal factor garch. Mimeo: University of Sussex.
Arditti, F., and H. Levy. 1976. Portfolio efficiency analysis in three moments: The multiperiod case. Journal of Finance 30: 797–809.
Aste, T., 2020. Topological regularization with information filtering networks. arXiv preprint http://arxiv.org/abs/2005.04692.
Aste, T., T. Di Matteo. 2017. Causality network retrieval from short time series. arXiv preprint http://arxiv.org/abs/1706.01954.
Aste, T., and T. Di Matteo. 2006. Dynamical networks from correlations. Physica A: Statistical Mechanics and its Applications 370: 156–161. https://doi.org/10.1016/j.physa.2006.04.019
Bamberg, G., and G. Dorfleitner. 2001. Fat tails and traditional capital market theory. Working Pape: University of Augsburg.
Barfuss, W., G.P. Massara, T. di Matteo, and T. Aste. 2016. Parsimonious modeling with information filtering networks. Physical Review E 94: 062306. https://doi.org/10.1103/PhysRevE.94.062306.
Batra, L., and H.C. Taneja. 2022. Portfolio optimization based on generalized information theoretic measures. Communications in Statistics - Theory and Methods 51(18): 6367-6384.
Bauwens, L., S. Laurent, and J.V.K. Rombouts. 2006. Multivariate garch models: a survey. Journal of Applied Econometrics 21 (1): 79–109.
Bawa, V.S. 1978. Safety-first, stochastic dominance, and optimal portfolio choice. Journal of Financial and Quantitative Analysis 13 (2): 255–271.
Bera, A.K., and M.L. Higgins. 1993. Arch models: Properties, estimation and testing. Journal of Economic Surveys 7 (4): 305–366.
Berkane, M., and P. Bentler. 1986. Moments of elliptically distributed random variates. Statistics & Probability Letters 4 (6): 333–335.
Black, F., and R. Litterman. 1992. Global portfolio optimization. Financial Analysts Journal 48 (5): 28–43.
Bollerslev, T., R. Chou, and K.F. Kroner. 1992. Arch modeling in finance: A review of the theory and empirical evidence. Journal of Econometrics 52 (1–2): 5–59.
Boudt, K., A. Galanos, S. Payseur, and E. Zivot. 2019. Chapter 7 - multivariate garch models for large-scale applications: A survey. In Conceptual econometrics using R. Vol. 41 of Handbook of statistics, ed. H.D. Vinod and C. Rao, 193–242. Amsterdam: Elsevier.
Brechmann, E.C., K. Hendrich, and C. Czado. 2013. Conditional copula simulation for systemic risk stress testing. Insurance: Mathematics and Economics 53 (3): 722–732.
Broadie, M. 1993. Computing efficient frontiers using estimated parameters. Annals of Operations Research 45: 215–229.
Brodie, J., I. Daubechies, C. De Mol, D. Giannone, and I. Loris. 2009. Sparse and stable markowitz portfolios. Proceedings of the National Academy of Sciences 106 (30): 12267–12272.
Caporin, M., and M. McAleer. 2012. Do we really need both bekk and dcc? a tale of two multivariate garch models. Journal of Economic Surveys 26 (4): 736–751.
Chamberlain, G. 1983. A characterization of the distributions that imply mean-variance utility functions. Journal of Economic Theory 29 (1): 185–201.
Cramér, H. 1946. Mathematical methods of statistics. Princeton landmarks in mathematics and physics. Princeton: Princeton University Press.
Daniels, H.E. 1965. The asymptotic efficiency of a maximum likelihood estimator. Matematika 9 (1): 149–161.
De Franco, C., J. Nicolle, and H. Pham. 2019. Bayesian learning for the Markowitz portfolio selection problem. International Journal of Theoretical and Applied Finance (IJTAF) 22 (07): 1–40.
Engle, R.F. 1982. Autoregressive conditional heteroscedasticity with estimates of the variance of united kingdom inflation. Econometrica 50 (4): 987–1007.
Fang, K., S. Kotz, and K. Ng. 1990. Symmetric multivariate and related distributions. No. 36 in Monographs on statistics and applied probability. London: Chapman & Hall.
Friedman, J., T. Hastie, and R. Tibshirani. 2008. Sparse inverse covariance estimation with the graphical lasso. Biostatistics 9 (3): 432–441.
Gollier, C. 2001. Wealth inequality and asset pricing. The Review of Economic Studies 68 (1): 181–203.
Han, C. 2020. A nonparametric approach to portfolio shrinkage. Journal of Banking & Finance 120: 105953.
Harlow, W.V. 1991. Asset allocation in a downside-risk framework. Financial Analysts Journal 47 (5): 28–40.
He, C., G. Li, H. Fan, and W. Wei. 2021. Correlation between shanghai crude oil futures, stock, foreign exchange, and gold markets: A garch-vine-copula method. Applied Economics 53 (11): 1249–1263.
Hogan, W.W., and J.M. Warren. 1974. Toward the development of an equilibrium capital-market model based on semivariance. Journal of Financial and Quantitative Analysis 9 (1): 1–11.
Jondeau, E., and M. Rockinger. 2006. The copula-garch model of conditional dependencies: An international stock market application. Journal of International Money and Finance 25 (5): 827–853.
Kremer, P.J., S. Lee, M. Bogdan, and S. Paterlini. 2020. Sparse portfolio selection via the sorted l1-norm. Journal of Banking & Finance 110: 105687.
Kritzman, M.P. 2000. Puzzles of finance: Six practical problems and their remarkable solutions. Wiley investment series. New York: John Wiley & Sons Inc.
Langford, E. 2006. Quartiles in elementary statistics. Journal of Statistics Education. https://doi.org/10.1080/10691898.2006.11910589.
Lassance, N., and F. Vrins. 2021. Portfolio selection with parsimonious higher comoments estimation. Journal of Banking & Finance 126: 106115.
Lauritzen, S.L. 1996. Graphical models. Oxford: Oxford University Press.
Ledoit, O., and M. Wolf. 2003. Improved estimation of the covariance matrix of stock returns with an application to portfolio selection. Journal of Empirical Finance 10 (5): 603–621.
Ledoit, O., and M. Wolf. 2004. A well-conditioned estimator for large-dimensional covariance matrices. Journal of Multivariate Analysis 88 (2): 365–411.
Ledoit, O. and M. Wolf. 2020. The power of (non-)linear shrinking: A review and guide to covariance matrix estimation. Journal of Financial Econometrics 20: 187–218. https://doi.org/10.1093/jjfinec/nbaa007
Li, D., and W.-L. Ng. 2000. Optimal dynamic portfolio selection : Multi-period mean-variance formulation. Mathematical Finance 10: 387–406.
Luca, G.D., G. Rivieccio, and S. Corsaro. 2020. Value-at-risk dynamics: A copula-var approach. The European Journal of Finance 26 (2–3): 223–237.
Mantegna, R., and H. Stanley. 2000. An introduction to econophysics: Correlations and complexity in finance. Cambridge: Cambridge University Press.
Mantegna, R.N. 1999. Hierarchical structure in financial markets. The European Physical Journal B - Condensed Matter and Complex Systems 11 (1): 193–197.
Markowitz, H. 1952. Portfolio selection. The Journal of Finance 7 (1): 77–91.
Maruyama, Y., and T. Seo. 2003. Estimation of moment parameter in elliptical distributions. Journal of the Japan Statistical Society 33: 215–229.
Massara, G. P., Aste, T., 2019. Learning clique forests. arXiv preprint http://arxiv.org/abs/1905.02266.
Massara, G. P., di Matteo, T., Aste, T., 2015. Network filtering for big data: Triangulated maximally filtered graph. http://arxiv.org/abs/1505.02445.
Mei, X., V. DeMiguel, and F.J. Nogales. 2016. Multiperiod portfolio optimization with multiple risky assets and general transaction costs. Journal of Banking & Finance 69: 108–120.
Mercurio, P.J., Y. Wu, and H. Xie. 2020. An entropy-based approach to portfolio optimization. Entropy 22 (3): 332.
Meucci, A., 2010. Fully flexible views: Theory and practice. https://ideas.repec.org/p/arx/papers/1012.2848.html
Michaud, R., 1989. The markowitz optimization enigma: Is optimized optimal? Working Paper, University of Augsburg (45), 31–42.
Michaud, R., and R. Michaud. 1998. Efficient asset management: A practical guide to stock portfolio optimization and asset allocation. Boston: Harvard Business School Press.
Nawrocki, D. 1996. Portfolio analysis with a large universe of assets. Applied Economics 28: 1191–1198.
Owen, J., and R. Rabinovitch. 1983. On the class of elliptical distributions and their applications to the theory of portfolio choice. The Journal of Finance 38 (3): 745–752.
Philippatos, G.C., and C.J. Wilson. 1972. Entropy, market risk, and the selection of efficient portfolios. Applied Economics 4 (3): 209–220.
Pola, G. 2016. On entropy and portfolio diversification. Journal of Asset Management 17 (4): 218–228.
Procacci, P.F., and T. Aste. 2019. Forecasting market states. Quantitative Finance 19 (9): 1491–1498.
Quaranta, A.G., and A. Zaffaroni. 2008. Robust optimization of conditional value at risk and portfolio selection. Journal of Banking & Finance 32 (10): 2046–2056.
Scherer, Bernd. 2006. Portfolio construction and risk budgeting. New York: Risk Books.
Scherer, B., K. Winston, and C. O’Cinneide. 2012. Bayesian methods in investing. Oxford: Oxford University Press.
Sklar, M. J. 1959. Fonctions de repartition a n dimensions et leurs marges.Publications de l’Institut Statistique de l’Université de Paris 8: 229-231.
Song, W.-M., T. Di Matteo, and T. Aste. 2012. Building complex networks with platonic solids. Physical Review E 85: 046115.
Tumminello, M., T. Aste, T. Di Matteo, and R.N. Mantegna. 2005. A tool for filtering information in complex systems. Proceedings of the National Academy of Science 102: 10421–10426.
Van Der Maaten, L., E. Postma, and J. Van den Herik. 2009. Dimensionality reduction: A comparative review. Journal of Machine Learning Research 10: 66–71.
van der Weide, R. 2002. Go-garch: A multivariate generalized orthogonal garch model. Journal of Applied Econometrics 17 (5): 549–564.
Wald, A. 1949. Note on the consistency of the maximum likelihood estimate. Annals of Mathematical Statistics 20 (4): 595–601.
Xing, X., J. Hu, and Y. Yang. 2014. Robust minimum variance portfolio with l-infinity constraints. Journal of Banking & Finance 46: 107–117.
Yao, H., J. Huang, Y. Li, and J. Humphrey. 2021. A general approach to smooth and convex portfolio optimization using lower partial moments. Journal of Banking & Finance 129: 106167.
Zhang, B., Y. Wei, J. Yu, X. Lai, and Z. Peng. 2014. Forecasting var and es of stock index portfolio: A vine copula method. Physica A: Statistical Mechanics and its Applications 416: 112–124.
Acknowledgements
The authors acknowledge partial support from ESRC (ES/K002309/1), EPSRC (EP/P031730/1) and EC (H2020-ICT-2018-2 825215).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The author declare that thye have no conflict of interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix A. Elliptical distributions
Consider an n-dimensional vector of multivariate returns \({\varvec{X}}=(x_{1},x_{2},...,x_{n})\). If \({\varvec{X}}\) is elliptical distributed, then its probability density function is defined as:
where \({\varvec{\mu }}\in {\mathbb {R}}^{1\times n}\) is the vector of location (mean) parameters and \(c_n\) is a normalization constant. The matrix, \({\varvec{J}} = {\varvec{\Omega }}^{-1} \in {\mathbb {R}}^{n\times n}\) is the generalized precision matrix, a positively defined matrix which is the inverse of the dispersion matrix \({\varvec{\Omega }}\). When the covariance is defined (as we assume in this paper) then \({\varvec{\Omega }}= (-\psi '(0))^{-1}{\varvec{\Sigma }}\), that is, \({\varvec{\Omega }}\) is proportional to the covariance matrix and the proportionality factor is the inverse of the first derivative of the characteristic generator evaluated at 0. The function, \(g_n(\cdot )\) is called density generator.
Also, let us stress that \(({\varvec{X}}-{\varvec{\mu }}) {\varvec{J}} ({\varvec{X}}-{\varvec{\mu }})^T\) - i.e., the generalized, square Mahalanobis distance - is a quadratic term and hence a nonnegative quantity provided that the matrix \({\varvec{\Omega }}\) is positive definite. To ease the notation, for the remaining of the paper we shall refer to the generalized Mahalanobis distance as \(d^2\):
For dfferent density generators \(g_n(\cdot )\) we obtain different distributions of the elliptical family. It is easy to see, for example, that the normal distribution is obtained by using:
and \({\varvec{\Omega }}= {\varvec{\Sigma }}\).
Similarly the Student-t distribution is obtained by using:
where v is the degrees of freedom, and \({\varvec{\Omega }}= \frac{\nu -2}{\nu } {\varvec{\Sigma }}\).
The validity of the mean–variance framework for elliptical distributions has long been established in literature (Owen and Rabinovitch 1983). This proposition is derived easily from two properties of the elliptical distributions. First, for every elliptical distribution with defined mean and variance, the distribution is completely specified by them ( Owen and Rabinovitch (1983) or Chamberlain (1983)), with all the higher moments being either zero or proportional to the first or second moment. Second, any linear combination of multivariate elliptically distributed variables is also an elliptically distributed variable. In the case of normal distribution and Student-t distribution they also have the same density generator function. Further details on these properties are provided in Appendix B.
It follows that, if asset returns have a multivariate elliptical distribution \({\varvec{X}} \sim {\mathcal {E}}_n({\varvec{\mu , \Omega }}, g_n)\), then the portfolio expected return and dispersion are given by, respectively, \({\mathbb {E}}[r_p]={\varvec{W\mu }}^T\) and \(\sigma _{p}={\varvec{W \Omega W^T}}\), matching the optimization framework outlined in ''Modern portfolio theory'' section.
With respect to our likelihood analysis, considering distributions with probability density function of the form specified in Eq. A.1, the corresponding likelihood function is of the form:
where ED denotes the general Elliptical Distributions and we omitted the constant of integration.
To stress the general validity of our analysis for other elliptical distributions, we repeated the experiments discussed in ''Methodology'' section considering the Student-t generator.
Assuming a Student-t distribution of the log returns, the log-likelihood (Eq. A.5) is:
where n is the sample size and \(\nu\) is the degree of freedom. Figure 10a reports the likelihood comparison for the same resamplings as in Fig. 3 but using a Student-t log-likelihood as in Eq. A.6. Here we used \(n=500\) observations (i.e., the out-of-sample size) and \(\nu =3\). We verified that this findings are robust across different degrees of freedom in the range \(\nu =[2.1,4]\).
Appendix B. Properties of elliptical distributions
In this section we recall some useful properties of Elliptical Distribution which we referred to in our discussion and particularly in Section A.
Property 1
(Distribution Definition) Consider an n-dimensional random vector \({\varvec{X}}=(X_1,...,X_n)\). \({\varvec{X}}\) has a multivariate elliptical distribution with location parameter \({\varvec{\mu }}\) and dispersion parameter \(\mathbf \Omega\),written as \({\varvec{X}} \sim {\mathcal {E}}({\varvec{\mu , \Omega }} )\) if its characteristic function \(\phi\) can be expressed as:
for some location parameter \({\varvec{\mu }} \in {\mathbb {R}}^{1\times n}\), positive-definite dispersion matrix \({\varvec{\Omega }} \in {\mathbb {R}}^{n\times n}\) and for some function \(\psi (\cdot ):[0,\infty ) \rightarrow {\mathbb {R}}\) such that \(\psi \left( \sum _{i=1}^{n}w^2_i \right)\) is a characteristic function, which is called characteristic generator. If \({\varvec{X}} \sim {\mathcal {E}}({\varvec{\mu , \Omega }} )\) and if its density \(f_X({\varvec{X}})\) exists, it is of the form defined in Eq. A.1.
Property 2
(Density Generator) The function \(g(\cdot )\) defined in Section Appendix A is guaranteed to be density generator if the following condition holds:
Property 3
(Affine Equivariance) If \({\varvec{X}}=(X_1,...,X_n)\) is an n-dimensional elliptical random variable with location parameter \({\varvec{\mu }}\) and dispersion parameter \({\varvec{\Omega }}\) so that \({\varvec{X}} \sim {\mathcal {E}}_X({\varvec{\mu , \Omega }} )\), then for any vector \({\varvec{a}} \in {\mathbb {R}}^{1\times m}\) and any matrix \({\varvec{B}}\in {\mathbb {R}}^{m\times n}\) the following affine equivariance holds:
In other words, any linear combination of multivariate elliptical distributions is another elliptical distribution.
In the special cases of normal, Student-t and Cauchy distributions, the induced density generators are m-dimensional version of the original generator of \({\varvec{X}}\).
For the proof of Properties 1, 2 and 3, we refer to Fang et al. (1990).
This implies that any portfolio \(Y = \beta _1 X_1+...+\beta _n X_n\) of elliptically distributed variables is distributed accordingly with a (univariate) elliptical distribution, which is a location-scale distribution. Furthermore, for any univariate elliptical distribution all moments can be obtained from the first and second moments (if defined). In particular, for centered variables with zero mean (\(\mu _Y=0\)), the resulting distribution of Y is symmetrical around zero and it has all odd moments equal to zero and all even moments given by:
with
Where \(\psi ^{(m)}(0)\) indicated the \(m^\mathrm{th}\) derivative of \(\psi (\omega )\) computed at \(\omega =0\).
As an example, in the normal (0,1) case, \(\mu _2=1\), \(c_m=0\) for all \(m=1,2,...\), the kurtosis is \(\mu _{(4)}=\frac{4!}{2^4 4!}=3\), and \(\mu _{(2m)}=\frac{(2m)!}{(2^m m!)}\). For the proof we refer to Berkane and Bentler (1986), which derived this property by succesive differentiation of \(\phi (\cdot )\), and to Maruyama and Seo (2003), which attained the same result by expressing the elliptical distribution in terms of a random vector with uniform distribution on the unit sphere.
Therefore, the mean–variance optimization is of general applicability and relevance for any portfolio generated from multivariate elliptically distributed variables.
Appendix C. Orthogonal GARCH estimation and further results
In this section, we report details on the O-GARCH estimation discussed in Section 6. In particular, Tables 3 and 4 report the average AIC and BIC statistics across the 100 resamplings we considered in the experiment. As discussed in ''O-GARCH comparison'' section, both the AIC and BIC criteria support a GARCH(1,1) specification.
Table 5 below reports Median, 5th and 95th percentiles all the statistics obtained. The table shows that the GARCH(1,1) specification delivered the lowest AIC and BIC statistics for each of the main percentiles considered. In other words, the GARCH(1,1) specification selected in our experiment is the preferred specification according to the AIC and BIC criteria in all cases, and not only in mean across resamplings.
Having selected the GARCH(1,1) specification, for each resampling we estimated the model parameters (Table 6 reports the estimated parameters and corresponding p-Values), forecasted one steps ahead principal components and then reconstruct the covariance matrix as in Eq. 5.
Having selected the O-GARCH(1,1) specification we performed the same experiments discussed in ''Impact of precision matrix estimate on optimal portfolios'' section to compare the optimal minimum variance portfolio features when the O-GARCH covariance is used in the optimization. Figure 11 reports the number of active long and short positions obtained with the O-GARCH covariance matrix. As discussed in ''O-GARCH comparison'' section, the O-GARCH positions closely track the full covariance behaviour leading to the same conclusions and instability problems.
Appendix D. Turnover comparison
In ''Backtest'' section we compared the performances and stability of daily rebalanced portfolios, constructed based on OGARCH and TMFG precision matrices. Particularly relevant for the purpose of this paper is the stability of portfolios to new observations that, from a practitioner standpoint, results in lower turnover and transaction costs. We reported the average turnover in Fig. 9, while Fig. 12 reports a histogram of all daily turnovers computed across 100 resamplings and comparing TMFG to OGARCH for each estimation window. The histograms show that, other than delivering a significantly lower turnover on average as noted in ''Backtest'' section, TMFG portfolios’ turnover is heavily positively skewed, with a pick in the distribution around zero, supporting and strengthening our claim of superior stability of TMFG portfolios.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Procacci, P.F., Aste, T. Portfolio optimization with sparse multivariate modeling. J Asset Manag 23, 445–465 (2022). https://doi.org/10.1057/s41260-022-00280-2
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1057/s41260-022-00280-2