Now- and Backcasting Initial Claims with High-Dimensional Daily Internet Search-Volume Data

Abstract

We propose an out-of-sample prediction approach that combines unrestricted mixed-data sampling with machine learning (mixed-frequency machine learning, MFML). We use the MFML approach to generate a sequence of now- and backcasts of weekly unemployment insurance initial claims based on a rich trove of daily Google Trends search-volume data for terms related to unemployment. The predictions are based on linear models estimated via the LASSO and elastic net, nonlinear models based on artificial neural networks, and ensembles of linear and nonlinear models. Now- and backcasts of weekly initial claims based on models that incorporate the information in the daily Google Trends terms substantially outperform those based on models that ignore the information, and predictive accuracy increases as the now- and backcasts include more recent daily Google Trends data. The relevance of daily Google Trends terms for predicting weekly initial claims is strongly linked to the COVID-19 crisis.