Economists and econometricians typically use aggregate economic and financial variables for gross domestic product (GDP) prediction. However, aggregation often results in a loss of valuable information, diminishing key features such as heterogeneity, interactions, nonlinearity, and structural breaks. We propose a novel microforecasting approach, using large panel data of firm accounting earnings from corporate financial reports to forecast GDP. By employing machine learning methods, we can effectively exploit this large microlevel information set to achieve substantially more accurate GDP forecasts. Our findings highlight the advantages and potential of utilizing microlevel data for macroprediction, diverging from the conventional macroforecasting paradigm that relies on aggregate data to forecast macrovariables.

Publication:

MANAGEMENT SCIENCE

http://dx.doi.org/10.1287/mnsc.2025.01549

Author:

Cui, Yumeng

Cent Univ Finance & Econ, Sch Econ, Beijing 102206, Peoples R China

Email address: cuiyumeng.0614@email.cufe.edu.cn

Huang, Naijing (corresponding author)

Cent Univ Finance & Econ, Sch Econ, Beijing 102206, Peoples R China

Email address: huang.naijing@cufe.edu.cn

Hong, Yongmiao

Chinese Acad Sci, Acad Math & Syst Sci, Natl Key Lab Math China, Beijing 100045, Peoples R China

Chinese Acad Sci, Acad Math & Syst Sci, Ctr Forecasting Sci, Beijing 100045, Peoples R China

Univ Chinese Acad Sci, Sch Econ & Management, Beijing 100190, Peoples R China

Univ Chinese Acad Sci, MOE Social Sci Lab Digital Econ Forecasts & Policy, Beijing 100190, Peoples R China

Email address: yh20@cornell.edu

Wang, Yicheng

Peking Univ, HSBC Business Sch, Shenzhen 518055, Peoples R China

Email address:wangyc@phbs.pku.edu.cn