A0890
Title: Nowcasting GDP using time-varying machine learning methods and mixed-frequency data
Authors: Giacomo Caterini - Italian Parliamentary Budget Office (Italy) [presenting]
Cecilia Frale - Italian Parliamentary Budget Office (Italy)
Libero Monteforte - Bank of Italy (Italy)
Abstract: Advances in data availability and storage have provided forecasters with an increasingly rich set of economic indicators. Given the delayed and uncertain release of official GDP figures, nowcasting models have emerged to estimate current-quarter activity in real time. The aim is to investigate the time-varying predictive power of large amounts of regressors available with mixed-frequency, exploiting machine learning models for dimensionality reduction and forecasting. Following this approach, it is found that quarterly Italian GDP forecasts based on machine learning algorithms fed by pseudo-real-time monthly information outperform the benchmark, accounting for varying data frequencies and publication lags, addressing the challenges of asynchronous indicator release.
