IPOhelper: Mining features in registration statements for listing prediction of technological innovation companies

Abstract

This paper develops IPOhelper based on statistical (financial, technological innovation indicators) and semantic cues (textual indicators) in registration statements, which is a novel predictive system for initial public offering (IPO) prediction. Based on 692 registration statements of technological innovation companies from 2019 to 2023, we found that the IPOhelper performs exceptionally well in predicting IPO outcomes. Compared with statistical cues, the predictive abilities of semantic features are particularly prominent. In particular, the semantic feature of “Technovation”, which reflects the adequacy of innovation-related information disclosure, is the most important feature for IPO prediction.