 Predicting IPO first-day returns: Evidence from machine learning analyses*Gonul Colak, Mengchuan Fu and Iftekhar Hasan Journal of Banking & Finance, 2025, vol. 178, issue C Abstract: Predicting IPO first-day returns is inherently challenging due to the wide range of contributing factors, each with distinct statistical properties. We assess the performance of several machine learning (ML) techniques and identify XGBoost as the most statistically effective model for forecasting first-day returns. Using a comprehensive set of 863 pre-IPO variables, our high-performing predictive model accurately estimates both the direction and magnitude of IPO first-day returns. The most influential predictors include underwriter agency measures, price revision, and the free-float fraction. Using a rolling-window predictive approach, the model demonstrates substantial practical value, generating approximately $300 billion in gains from IPOs with positive first-day returns and avoiding more than $22 billion in losses from those with negative returns over the 2000–2016 period. Keywords: Machine learning; Initial public offering; IPO first-day returns; Return prediction; eXtreme gradient boosting; IPO underpricing (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:jbfina:v:178:y:2025:i:c:s0378426625001207 DOI: 10.1016/j.jbankfin.2025.107500 Access Statistics for this article Journal of Banking & Finance is currently edited by Ike Mathur More articles in Journal of Banking & Finance from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.