Aggregate Learning for Mixed Frequency Data

TL;DR

This paper introduces a mixed-frequency aggregate learning model that leverages real-time alternative data to predict regional economic indicators, capturing heterogeneity and rapid changes in economic conditions.

Contribution

The paper proposes a novel MF-AGL model utilizing spatio-temporal alternative data for real-time economic prediction at small-area levels.

Findings

Predicts regional heterogeneity in labor markets

Captures rapid economic status changes

Effective for real-time economic analysis

Abstract

Large and acute economic shocks such as the 2007-2009 financial crisis and the current COVID-19 infections rapidly change the economic environment. In such a situation, the importance of real-time economic analysis using alternative datais emerging. Alternative data such as search query and location data are closer to real-time and richer than official statistics that are typically released once a month in an aggregated form. We take advantage of spatio-temporal granularity of alternative data and propose a mixed-FrequencyAggregate Learning (MF-AGL)model that predicts economic indicators for the smaller areas in real-time. We apply the model for the real-world problem; prediction of the number of job applicants which is closely related to the unemployment rates. We find that the proposed model predicts (i) the regional heterogeneity of the labor market condition and (ii) the rapidly changing economic status. The model can be applied to various tasks, especially economic analysis