Text Mining for Studying Management's Confidence in IPO Prospectuses and IPO Valuations

Understanding pricing strategies in the context of the Initial Public Offering (IPO) process has been receiving much attention. Most prior studies have however focused on information sources from post issuance periods, and understanding such strategies from the management’s perspective during the IPO process is still an open research issue. Form 424 variants, as finalized IPO prospectus approved by Security Exchange Committee (SEC), contain rich and genuine information about the issuing firms. In this study, we analyze the inter-relationships between the management’s confidence (through the proxy of sentiments expressed in textual contents in the Management’s Discussion & Analysis (MD&A) sections in the prospectus) and the pre-/post-IPO valuations. We develop an analytical framework namely FOCAS-IE (Feature-Oriented, Context-Aware, Systematic Information Extraction) to derive sentiments from the MD&A sections. Further, we construct predictive models using information extracted using FOCAS-IE to predict IPO pricings. The results have shown to outperform results from prior related studies.

[1]  Yuefeng Li,et al.  Effective Pattern Discovery for Text Mining , 2012, IEEE Transactions on Knowledge and Data Engineering.

[2]  Omar F. El-Gayar,et al.  Term Extraction and Disambiguation for Semantic Knowledge Enrichment: A Case Study on Initial Public Offering (IPO) Prospectus Corpus , 2015, 2015 48th Hawaii International Conference on System Sciences.

[3]  Anthony J. T. Lee,et al.  Stock price movement prediction using representative prototypes of financial reports , 2011, ACM Trans. Manag. Inf. Syst..

[4]  Tim Loughran,et al.  When is a Liability not a Liability? Textual Analysis, Dictionaries, and 10-Ks , 2010 .

[5]  Dirk Neumann,et al.  Automated news reading: Stock price prediction based on financial news using context-capturing features , 2013, Decis. Support Syst..

[6]  Harjeet S. Bhabra,et al.  IPO Prospectus Information and Subsequent Performance , 2003 .

[7]  Kalina Bontcheva,et al.  GATE: an Architecture for Development of Robust HLT applications , 2002, ACL.

[8]  Tomer Geva,et al.  Empirical evaluation of an automated intraday stock recommendation system incorporating both market data and textual news , 2014, Decis. Support Syst..

[9]  Gerard Hoberg,et al.  The Information Content of IPO Prospectuses , 2009 .

[10]  ChenHsinchun,et al.  Textual analysis of stock market prediction using breaking financial news , 2009 .

[11]  Ivo Welch,et al.  A Review of IPO Activity, Pricing and Allocations , 2002 .

[12]  G. Shmueli,et al.  The Challenge of Prediction in Information Systems Research , 2009 .

[13]  Bill McDonald,et al.  IPO First-Day Returns, Offer Price Revisions, Volatility, and Form S-1 Language , 2013 .

[14]  Tom Arnold,et al.  The Effects of Ambiguous Information on Initial and Subsequent IPO Returns , 2010 .

[15]  David Goldreich,et al.  Investor Sentiment and Pre-IPO Markets , 2006 .

[16]  Feng Li.  The Information Content of Forward-Looking Statements in Corporate Filings—A Naïve Bayesian Machine Learning Approach , 2010 .

[17]  Stephen P. Ferris,et al.  The Effect of Issuer Conservatism on IPO Pricing and Performance , 2012 .

[18]  Xue-wen Chen,et al.  Combating the Small Sample Class Imbalance Problem Using Feature Selection , 2010, IEEE Transactions on Knowledge and Data Engineering.

[19]  Lara Khansa,et al.  Predicting stock market returns from malicious attacks: A comparative analysis of vector autoregression and time-delayed neural networks , 2011, Decis. Support Syst..

[20]  Gerard Hoberg,et al.  Litigation Risk, Strategic Disclosure and the Underpricing of Initial Public Offerings , 2011 .

[21]  Tim Loughran,et al.  Why Has IPO Underpricing Increased Over Time , 2002 .