In this note we revisit the empirical results in Bianchi, Büchner, and Tamoni (2020) after correcting for using information not available at the time the forecast was made. Although we note a decrease in out-of-sample $R^2$, the revised analysis confirms that bond excess return predictability from neural networks remains statistically and economically significant.

dx.doi.org/10.1093/rfs/hhaa098, hdl.handle.net/1765/134902
The Review of Financial Studies
Erasmus University Rotterdam

Bianchi, D. (Daniele), Büchner, M. (Matthias), Hoogteijling, T. (Tobias), & Tamoni, A. (Andrea). (2021). Corrigendum: Bond Risk Premiums with Machine Learning. The Review of Financial Studies, 34(2), 1090–1103. doi:10.1093/rfs/hhaa098