We show that machine learning methods, in particular extreme trees and neural networks (NNs), provide strong statistical evidence in favor of bond return predictability. NN forecasts based on macroeconomic and yield information translate into economic gains that are larger than those obtained...

We study drift and cyclical components in U.S. Treasury bonds. We find that bond yields are drifting because they reflect the drift in monetary policy rates. Empirically, modeling the monetary policy drift using demographics and productivity trends, plus long-term inflation expectations, leads...

Fiscal policy matters for bond risk premia. Empirically, government spending level and volatility predict excess bond returns. Shocks to government spending level and volatility are also priced in the cross-section of bond and stock portfolios. Theoretically, level shocks raise inflation when...

We show that the difference between the natural rate of interest and the current level of monetary policy stance, which we label Convergence Gap (CG), contains information that is valuable for bond predictability. Adding CG in forecasting regressions of bond excess returns significantly raises...