Real-Time Macro Information and Bond Return Predictability

Friday 23 September 2022

This paper proposes a weighted group neural network model and reexamines whether treasury bond returns are predictable when real-time, instead of fully-revised, macro information is used. Real-time macro vintage data and news-based topic attention are taken into account. We find that news contains rich information on future bond returns beyond traditional macro variables.

To find more, download the full Working Paper (EN) 

A Weighted Group Deep Learning Approach