Subscribe to DSC Newsletter

Natural Language Understanding (NLU) in Enterprise – Digesting IPO Prospectus

Introduction

Business ventures based on existing or disruptive business models taking on the route of Initial Public Offering are always a challenge to investors who want to profit from early investment into those would be “unicorn IPO”. A good investment may get worse before it gets better. Others may get worse and never recover. Aside from the macroeconomics and consumer trends that could affect the outcome of such investments, the fundamentals of these new public offerings are presented by its founders in the SEC form S-1 filing or IPO prospectus. These filings provide a view into the quantitative and qualitative components of new business ventures that are scheduled to be traded as public equities in the exchanges. A substantial part of these challenges to investors is to learn about the different aspects presented in an S-1 which are comprised of people, technology, events, places, and economic models that are being described in the founders’ words. Some of these words are acronyms, names of things or concepts that are unique to a new business. Although most of these new terms are somehow explained within these documents, prevailing technology on NLU often requires domain specific ontologies and dictionaries for the underlying software to decipher the meaning in these documents.

 

The Solution 

The technology is called “Communication In Focus” (or CIF), a NLU technology that is based on a novel approach that does not require the pre-definition of these terms. Rather, the design uses Context Discriminants to digest these new subjects based on prior understanding of the based language. Context Discriminant reduces complex documents into snippets of words of semantic neighbors consisting of context and points of views on subjects. Higher order derivatives are achieved by applying CD to the result produced by the prior CD. This approach enables us to refine the contexts on related subjects over distant semantic neighbors and to discover higher order dependent subjects that depict entity relationships between subjects.

 

CD analysis of an IPO prospectus does not replace the actual document. Rather, CD is a tool that amplifies analytical field of vision. By rapidly self-discovering points of interest in complex textual data that may undermine (or confirm) a potential investment opportunity, CD method enables investors & organizations to see more, act faster, and make smarter decisions. 

 

Conclusion

My team has applied this calculus to several S-1 filings and found it highly effective in pinpointing risks and issues of new business ventures, while highlighting the qualitative merit at the same time. For investors, this tool has the potential to augment and amplify analytic capacity, enabling users to quickly size up the qualitative component of an IPO prospectus before strategically diving into quantitative components for validation. For reference, my team has pivoted our analytics – using a common set of parameters – to yield a set of analytic reports on several outstanding IPO prospectuses previously published on the SEC’s website. Each report is automatically generated by the CIF NLU engine end-to-end. We look forward to hearing from readers for feedback and comments. 

Views: 897

Tags: AI, NLP, NLU, analytics, artificial, dark, data, intelligence, language, natural, More…processing, text, understanding, unstructured

Comment

You need to be a member of Data Science Central to add comments!

Join Data Science Central

Videos

  • Add Videos
  • View All

© 2019   Data Science Central ®   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service