PERC | Thematic Investing with Big Data: The Case of Private Equity

By Ludovic Phalippou, University of Oxford - Said Business School

The purpose of this study was to design a flexible and automated index of publicly traded securities that have a high correlation with private equity fund market returns. Using natural language processing, the author scored each company based on the frequency with which news articles and press releases mentioned its name along with the terms “private equity” and “leveraged buy-out”. An index was then created with the weights set as a function of the company’s exposure to these terms.

The study shows that the listed private equity index is highly correlated to commonly used private equity fund market indices; there is a nearly 90% correlation with the Burgiss LBO fund index, which is one of the most commonly used benchmarks in private equity.