IPO Underpricing and Prospectus Readability: A Machine Learning Approach

Authors

  • Christophor Sai Kit Tsui The Open University of Hong Kong
  • Kevin Chi Keung Li The Open University of Hong Kong

DOI:

https://doi.org/10.33423/jabe.v23i7.4867

Keywords:

business, economics, IPO, underpricing, machine learning

Abstract

IPO prospectus is the crucial document available to investors, allowing investors to understand the company and the IPO. IPO underpricing occurs when the closing price of the initial public offer (IPO) is higher than the offering price on its first trading day. If investors know whether the IPO is likely to be underpriced, they can earn a significant return by subscribing to those underpriced IPOs and selling the shares on the first trading day. In this study, the relationships between the readability of the IPO prospectus and IPO underpricing of firms listed in the Hong Kong Stock Exchange are analyzed using the gradient boost decision tree approach. This study shows that the readability scores of the chapters in the IPO prospectus are relevant to identify underpriced IPOs. Additionally, several indicators are more crucial to identify underpriced IPOs.

Downloads

Published

2021-12-29

How to Cite

Tsui, C. S. K., & Kevin Chi Keung Li. (2021). IPO Underpricing and Prospectus Readability: A Machine Learning Approach. Journal of Applied Business and Economics, 23(7). https://doi.org/10.33423/jabe.v23i7.4867

Issue

Section

Articles