This paper analyses the forecasting performance of monetary policy reaction functions using U.S. Federal Reserve's Greenbook real-time data. The results indicate that artificial neural networks are able to predict the nominal interest rate better than linear and nonlinearTaylor rule models as...

We analyze the influence of monetary policy on firms’ extensive margin and productivity. Our empirical evidence for the U.S. based on a macro-financial SVAR suggests that expansionary monetary policy shocks stimulate corporate profits, reduce firm exit and increase firm entry. In the medium...

This paper identifies U.S. monetary and fiscal dominance regimes using machine learning techniques. The algorithms are trained and verified by employing simulated data from Markov-switching DSGE models, before they classify regimes from 1968-2017 using actual U.S. data. All machine learning...

This paper proposes a tractable financial accelerator New Keynesian DSGE modelthat allows for closed-form solutions. In the presence of financial frictions, theNew Keynesian Phillips curve features a flat slope with respect to the output gapand is strongly forward-looking. All shocks cause...

This paper introduces a reinforcement learning based approach to compute optimal interest rate reaction functions in terms of fulfilling inflation and output gap targets. The method is generally flexible enough to incorporate restrictions like the zero lower bound, nonlinear economy structures...