Nowcasting inflation with Lasso-regularized vector autoregressions and mixed frequency data

Abstract

We evaluate the predictive performances of the least absolute shrinkage and selection operator (Lasso) as an alternative shrinkage method for high-dimensional vector autoregressions. The analysis extends the Lasso-based multiple equations regularization to a mixed/high-frequency data setting. Very short-term forecasting (nowcasting) is used to target the Euro area's inflation rate. We show that this approach can outperform more standard nowcasting tools in the literature, producing nowcasts that closely follow actual data movements. The proposed tool can overcome information and policy decision problems related to the substantial publishing delays of macroeconomic aggregates.