Real-Time Macro Information and Bond Return Predictability: Does Deep Learning Help?

Abstract

This paper examines whether deep/machine learning can help find any statistical and/or economic evidence of out-of-sample bond return predictability when real-time, instead of fully-revised, macro variables are taken as predictors. First, when using pure real-time macro information alone, we find that deep learning cannot help find any statistical evidence for forecasting both non-overlapping and overlapping excess bond returns. In contrast, some machine learning models can help find some statistical evidence for forecasting overlapping excess bond returns. Second, when using both pure real-time macro information and yield curve information, we find that deep learning performs well for forecasting medium- and long-maturity overlapping excess bond returns, but such predictability is dominantly driven by yield curve information. Third, all statistical evidence of predictability is much weaker than that found from using fully-revised macro data and generates minimal economic gains for a mean-variance investor, regardless of her level of risk aversion and whether she can take short positions.