Feature selection for portfolio optimization
MetadataShow full item record
SubjectAgglomerative hierarchical clustering; Parameter uncertainty; Portfolio optimization; Feature selection
Most portfolio selection rules based on the sample mean and covariance matrix perform poorly out-of-sample. Moreover, there is a growing body of evidence that such optimization rules are not able to beat simple rules of thumb, such as 1/N. Parameter uncertainty has been identified as one major reason for these findings. A strand of literature addresses this problem by improving the parameter estimation and/or by relying on more robust portfolio selection methods. Independent of the chosen portfolio selection rule, we propose using feature selection first in order to reduce the asset menu. While most of the diversification benefits are preserved, the parameter estimation problem is alleviated. We conduct out-of-sample back-tests to show that in most cases different well-established portfolio selection rules applied on the reduced asset universe are able to improve alpha relative to different prominent factor models.
Showing items related by title, author, creator and subject.
Bjerring T; Rasmussen K; Weissensteiner A (2018)We investigate whether the returns of some industry portfolios predict the returns of other industry portfolios. We find a strong lead-lag structure which is statistically and economically significant. These findings suggest ...
Pettenuzzo, D ,Ravazzolo F (2016)We propose a density combination approach featuring combination weights that depend on the past forecast performance of the individual models entering the combination through a utility-based objective function. We apply ...
Use of sourdough made with quinoa (Chenopodium quinoa) flour and autochthonous selected lactic acid bacteria for enhancing the nutritional, textural and sensory features of white bread Rizzello CG; Lorusso A; Montemurro M; Gobbetti M (2016)Lactic acid bacteria were isolated and identified from quinoa flour, spontaneously fermented quinoa dough, and type I quinoa sourdough. Strains were further selected based on acidification and proteolytic activities. ...