Beyond Black–Litterman: Letting the Data Speak

Abstract

The Black–Litterman model is a popular approach to asset allocation that blends an investor’s proprietary views with the views of the market. The model ignores, however, the data-generating process, whose dynamics can significantly impact future portfolio returns. In this article, Zhou extends the Black–Litterman model to allow Bayesian learning to exploit all available information—market views, proprietary investor views, and the data. The framework allows practitioners to combine insights from the Black–Litterman model with the data to generate potentially more reliable trading strategies and more robust portfolios. Further, the author demonstrates that many Bayesian learning tools can be readily applied to practical portfolio selections in conjunction with the Black–Litterman model.

TOPICS: Portfolio construction, quantitative methods, portfolio theory