Nowcasting Distributional National Accounts for the United States: A Machine Learning Approach

Inequality statistics are usually calculated from high-quality microdata, typically available with a one-to-two-year lag. In turbulent times, policymakers and data users need timely estimates. We use an elastic net to nowcast the overall Gini coefficient and quintile-level income shares of personal income published by the US Bureau of Economic Analysis. The nowcasts (2020-2023) predict turning points with at least 90 percent accuracy across all metrics and significantly less error than naive models. We find that we can create advance inequality estimates approximately one month after the end of the calendar year, reducing the present lag by almost a year.