Optimizing Return Forecasts: A Bayesian Intermediary Asset Pricing Approach

Abstract

In this study, we propose an innovative Bayesian method to estimate panel break model, using economically motivated priors derived from intermediary asset pricing models. Our approach enhances the panel break model by integrating financial frictions and merging cross-sectional and time-series data. This amalgamation facilitates the regime change identification, selection of return predictors, and the estimation of factor premia, bolstering the forecasting of equity returns. We benchmark our model against the leading Bayesian forecasting technique of Smith and Timmermann (2019), demonstrating superior performance via both simulation and empirical data. Our model underscores the importance of leveraging asset holdings data and integrating intermediary friction logic for accurately detecting real-time regime changes tied to significant market events. These advancements lead to marked improvements in out-of-sample performance, illustrated by substantial cumulative returns and a superior Sharpe ratio.

Keywords: Cross-sectional risk premia variation; Bayesian analysis; Regime change; Model instability and model uncertainty; Intermediary asset pricing; Institution holdings data