Skip to Main Content
HBS Home
  • About
  • Academic Programs
  • Alumni
  • Faculty & Research
  • Baker Library
  • Giving
  • Harvard Business Review
  • Initiatives
  • News
  • Recruit
  • Map / Directions
Faculty & Research
  • Faculty
  • Research
  • Featured Topics
  • Academic Units
  • …→
  • Harvard Business School→
  • Faculty & Research→
Publications
Publications
  • 2020
  • Working Paper
  • HBS Working Paper Series

Is Accounting Useful for Forecasting GDP Growth? A Machine Learning Perspective

By: Srikant Datar, Apurv Jain, Charles C.Y. Wang and Siyu Zhang
  • Format:Print
  • | Language:English
  • | Pages:59
ShareBar

Abstract

We provide a comprehensive examination of whether, to what extent, and which accounting variables are useful for improving the predictive accuracy of GDP growth forecasts. We leverage statistical models that accommodate a broad set of (341) variables—outnumbering the total time-series observations—and apply machine learning techniques to train, validate, and test the prediction models. For near-term (current and next-quarter) GDP growth, accounting does not improve the out-of-sample accuracy of predictions because the professional forecasters' predictions are relatively efficient. Accounting's predictive usefulness increases for more-distant-term (three- and four-quarters-ahead) GDP growth forecasts: they contribute more to the model's predictions; moreover, their inclusion increases the model's out-of-sample predictive accuracy by 13 to 46%. Overall, four categories of accounting variables—relating to profits, accrual estimates (e.g., loan loss provisions or write-offs), capital raises or distributions, and capital allocation decisions (e.g., investments) are most informative of the longer-term outlook of the economy.

Keywords

Big Data; Elastic Net; GDP Growth; Machine Learning; Macro Forecasting; Short Fat Data; Accounting; Economic Growth; Forecasting and Prediction; Analytics and Data Science

Citation

Datar, Srikant, Apurv Jain, Charles C.Y. Wang, and Siyu Zhang. "Is Accounting Useful for Forecasting GDP Growth? A Machine Learning Perspective." Harvard Business School Working Paper, No. 21-113, December 2020.
  • SSRN
  • Read Now

About The Authors

Srikant M. Datar

→More Publications

Charles C.Y. Wang

Accounting and Management
→More Publications

More from the Authors

    • May 2025
    • Faculty Research

    A Decade of Corporate Governance Reform in Japan (2013-2023)

    By: Charles C.Y. Wang and Akiko Kanno
    • March 2025
    • Faculty Research

    Silicon Valley Bank: Gone in 36 Hours

    By: Jung Koo Kang, Krishna G. Palepu, Charles C.Y. Wang and David Lane
    • 2025
    • Faculty Research

    Centralized Governance in Decentralized Organizations

    By: Lin William Cong, Daniel Rabetti, Charles C.Y. Wang and Yu Yan
More from the Authors
  • A Decade of Corporate Governance Reform in Japan (2013-2023) By: Charles C.Y. Wang and Akiko Kanno
  • Silicon Valley Bank: Gone in 36 Hours By: Jung Koo Kang, Krishna G. Palepu, Charles C.Y. Wang and David Lane
  • Centralized Governance in Decentralized Organizations By: Lin William Cong, Daniel Rabetti, Charles C.Y. Wang and Yu Yan
ǁ
Campus Map
Harvard Business School
Soldiers Field
Boston, MA 02163
→Map & Directions
→More Contact Information
  • Make a Gift
  • Site Map
  • Jobs
  • Harvard University
  • Trademarks
  • Policies
  • Accessibility
  • Digital Accessibility
Copyright © President & Fellows of Harvard College.