Forecasting low‐frequency macroeconomic events with high‐frequency data

High-frequency financial and economic indicators are usually time-aggregated before computing forecasts of macroeconomic events, such as recessions. We propose a mixed-frequency alternative that delivers high-frequency probability (including their confidence bands) for low-frequency events. The new approach is compared with single-frequency alternatives using loss functions rare-event forecasting. find (i) the weekly-sampled term spread improves over monthly-sampled to predict NBER recessions, (ii) predictive content variables supplementary activity vulnerability (iii) weekly index can date 2020 business cycle peak in real-time filtering.