A Machine Learning Classifier for Corporate Opportunity Waivers

10 Pages Posted: 9 Oct 2016 Last revised: 5 Dec 2016

See all articles by Gabriel V. Rauterberg

Gabriel V. Rauterberg

University of Michigan Law School

Eric L. Talley

Columbia University - School of Law; European Corporate Governance Institute (ECGI)

Date Written: October 7, 2016

Abstract

Rauterberg & Talley (2017) develop a data set of “corporate opportunity waivers” (COWs) — significant contractual modifications of fiduciary duties — sampled from SEC filings. Part of their analysis utilizes a machine learning (ML) classifier to extend their data set beyond the hand-coded sample. Because the ML approach is likely unfamiliar to some readers, and in the light of its great potential across other areas of law and finance research, this note explains the basic components using a simple example, and it demonstrates strategies for calibrating and evaluating the classifier.

Keywords: Machine Learning, Big Data, Natural Language Processing, Corporate Opportunity Waivers, Fiduciary Duties, Corporate Finance, Corporate Governance, Corporate Law

JEL Classification: C80, K00, O16, G3, G34

Suggested Citation

Rauterberg, Gabriel V. and Talley, Eric L., A Machine Learning Classifier for Corporate Opportunity Waivers (October 7, 2016). Columbia Law and Economics Working Paper No. 553, Available at SSRN: https://ssrn.com/abstract=2849491 or http://dx.doi.org/10.2139/ssrn.2849491

Gabriel V. Rauterberg

University of Michigan Law School ( email )

625 South State Street
Ann Arbor, MI 48109-1215
United States

Eric L. Talley (Contact Author)

Columbia University - School of Law ( email )

435 West 116th Street
New York, NY 10025
United States

HOME PAGE: http://www.erictalley.com

European Corporate Governance Institute (ECGI) ( email )

c/o the Royal Academies of Belgium
Rue Ducale 1 Hertogsstraat
1000 Brussels
Belgium

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
246
Abstract Views
1,639
rank
158,987
PlumX Metrics