Title | ||
---|---|---|
Improving portfolios global performance using a cleaned and robust covariance matrix estimate. |
Abstract | ||
---|---|---|
This paper presents how the use of a cleaned and robust covariance matrix estimate can improve significantly the overall performance of maximum variety and minimum variance portfolios. We assume that the asset returns are modelled through a multi-factor model where the error term is a multivariate and correlated elliptical symmetric noise extending the classical Gaussian assumptions. The factors are supposed to be unobservable and we focus on a recent method of model order selection, based on the random matrix theory to identify the most informative subspace and then to obtain a cleaned (or de-noised) covariance matrix estimate to be used in the maximum variety and minimum variance portfolio allocation processes. We apply our methodology on real market data and show the improvements it brings if compared with other techniques especially for non-homogeneous asset returns. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/s00500-020-04840-9 | Soft Computing |
Keywords | DocType | Volume |
Portfolio selection, Maximum variety portfolio, Minimum variance portfolio, Covariance matrix, Random matrix theory, Thresholding, Factor model, Elliptic distribution | Journal | 24 |
Issue | ISSN | Citations |
12 | 1432-7643 | 0 |
PageRank | References | Authors |
0.34 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Emmanuelle Jay | 1 | 17 | 4.90 |
Thibault Soler | 2 | 0 | 0.34 |
Eugenie Terreaux | 3 | 1 | 1.04 |
Jean Philippe Ovarlez | 4 | 190 | 25.11 |
Frédéric Pascal | 5 | 175 | 23.99 |
Philippe de Peretti | 6 | 0 | 1.01 |
Christophe Chorro | 7 | 0 | 0.34 |