Incorporating uncertainty into the Black-Litterman portfolio selection model

We present a robust Black-Litterman (BL) model that takes into account the possibility of model misspecification. In place of a single prior distribution, we utilize multiple priors around the estimated expected excess returns and covariance matrix. The model has two primary advantages over the original BL model: (1) it systematically incorporates model misspecification in the form of Kullback-Leibler (KL) divergence and (2) by explicitly targeting robust allocations, it improves upon traditional bootstrap approaches.