Open Access
March 2020 Optimal asset allocation with multivariate Bayesian dynamic linear models
Jared D. Fisher, Davide Pettenuzzo, Carlos M. Carvalho
Ann. Appl. Stat. 14(1): 299-338 (March 2020). DOI: 10.1214/19-AOAS1303


We introduce a fast, closed-form, simulation-free method to model and forecast multiple asset returns and employ it to investigate the optimal ensemble of features to include when jointly predicting monthly stock and bond excess returns. Our approach builds on the Bayesian dynamic linear models of West and Harrison (Bayesian Forecasting and Dynamic Models (1997) Springer), and it can objectively determine, through a fully automated procedure, both the optimal set of regressors to include in the predictive system and the degree to which the model coefficients, volatilities and covariances should vary over time. When applied to a portfolio of five stock and bond returns, we find that our method leads to large forecast gains, both in statistical and economic terms. In particular, we find that relative to a standard no-predictability benchmark, the optimal combination of predictors, stochastic volatility and time-varying covariances increases the annualized certainty equivalent returns of a leverage-constrained power utility investor by more than 500 basis points.


Download Citation

Jared D. Fisher. Davide Pettenuzzo. Carlos M. Carvalho. "Optimal asset allocation with multivariate Bayesian dynamic linear models." Ann. Appl. Stat. 14 (1) 299 - 338, March 2020.


Received: 1 January 2019; Revised: 1 September 2019; Published: March 2020
First available in Project Euclid: 16 April 2020

zbMATH: 07200173
MathSciNet: MR4085095
Digital Object Identifier: 10.1214/19-AOAS1303

Keywords: 62C10 , 62P20 , 91B28 , 91B84

Rights: Copyright © 2020 Institute of Mathematical Statistics

Vol.14 • No. 1 • March 2020
Back to Top