来源：市场资讯

（来源：经济管理学刊）

打开网易新闻 查看精彩图片

近日，由中央财经大学经济学院的崔雨濛、黄乃静，中国科学院大学的洪永淼教授，北京大学汇丰商学院的汪意成的合作论文《预测GDP新范式——海量企业财报数据蕴藏的宏观密码》（Forecasting GDP Growth Rates Using Accounting Earnings: A Large Panel Microdata Approach）在《管理科学》（Management Science）发表。

打开网易新闻 查看精彩图片

# 论文简介 #

Title：

Forecasting GDP Growth Rates Using Accounting Earnings: A Large Panel Microdata Approach

Author：

Yumeng Cui, Yongmiao Hong, Naijing Huang, Yicheng Wang

Abstract：

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.

标题：

预测GDP新范式——海量企业财报数据蕴藏的宏观密码

中文摘要：

经济学家和计量经济学家通常使用总体经济和金融变量来预测国内生产总值（GDP）。然而，数据汇总往往导致有价值信息的损失，削弱了诸如异质性、交互作用、非线性和结构突变等关键特征。我们提出了一种新颖的微观预测方法，利用企业财务报告中大规模的面板数据——公司会计盈余来预测GDP。通过运用机器学习方法，我们能够有效挖掘这一庞大的微观信息集，从而实现更为精准的GDP预测。我们的研究结果揭示了利用微观数据进行宏观预测的优势与潜力，这不同于依赖汇总数据来预测宏观变量的传统宏观预测范式。