Textual Information and IPO Underpricing: A Machine Learning Approach

This study examines the predictive power of textual information from S-1 filings in explaining initial public offering (IPO) underpricing. The authors’ approach differs previous research because they utilize several machine learning algorithms to predict whether an IPO will be underpriced or not, as well magnitude Using a sample 2,481 US IPOs, find that can effectively complement financial variables terms prediction accuracy models use both sources data produce more accurate estimates. In particular, model with best performance using only achieves 67.5% whereas and appears substantial improvement (6.1%). Also, sophisticated drives increase compared traditional logistic regression (2.5%). authors attribute findings fact reduce ex ante valuation uncertainty firms. Finally, create portfolio IPOs based on out-of-sample predictions, which remarkably 27.90% average returns. Their extraordinary abnormal returns various time dimensions (both short long run), achieving up 30% better yield than benchmark.