The standard noninformative prior for Bayesian portfolio selection implies strong and unreasonable prior information about the achievable Sharpe ratio. This has critical implications for portfolio selection. We develop a reparametrization that allows to specify a prior which is flat in the...

This article shows how sparse solutions can be generated in parametric portfolio selection methods. Sparse mean-variance optimization procedures can be applied after the translation of parametric weight estimates into implied mean return estimates. The results of our empirical analysis suggest...

This article shows how asset characteristics can be incorporated into the Bayesian portfolio selection framework. We use Gaussian process priors to model the belief that assets with similar characteristics are likely to have similar expected returns. The resulting Bayesian shrinkage estimator...