Thematic Investing with Big Data: The Case of Private Equity

Abstract

Using natural language processing, we score companies based on the frequency with which news articles contain both their names and terms private equity and leveraged buy-out. An index is then created and can be updated seamlessly at high frequency. The weights are set as a function of the relative exposure to this theme. We add liquidity constraints to ensure minimal transaction costs. Even though the algorithm does not optimize on either return or correlation, this listed private equity index is highly correlated to commonly used private equity fund market indices: nearly 90% correlation with Burgiss LBO fund index. In addition, our index has similar returns as non-tradable Leveraged Buy-Outs (LBO) fund indices. Our approach can be generalized to many other investment themes.

Keywords:

• big data
• natural language processing
• private equity
• thematic investing

PL Credits: 0.75:

Acknowledgment

I am thankful to Paul Alazard for excellent research assistance. An early version of this study was commissioned by J.P. Morgan Securities plc.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 Source: https://pro.preqin.com/analysis/dryPowderAUM

2 The most-often cited index is the Cambridge Associates Global PE Index, but this index is no longer publicly available. We have its quarterly return for the period 2008–2019. For this time period, Burgiss averages 9.96% and Cambridge Associates averages 10.01% (annualized), and the correlation between the two is 99.6%. Preqin LBO index is increasingly used in practice and enable us to test the robustness of our results to the use of Burgiss data.

3 RavenPack also enables to detect different stories on similar events using a Novelty score, thereby filtering for stories within the day to avoid duplicates (referred as novel articles in this paper).

4 Blackstone Mortgage Trust is a publicly traded closed-ended fund holding real estate mortgages.

5 Ares has an AUM of $149 billion, but only $22 billion is in PE, while the rest is in private debt: direct lending to middle market companies, mostly in connection with leveraged buy-outs, but not exclusively.

6 Cannae is a relatively small and diversified holding company (restaurants, healthcare, finance). From the company’s website, it is difficult to tell whether it is more akin to a hedge fund or a growth capital fund. It does not seem to use leverage and that might be why terms such as LBOs and PE are never mentioned in related news articles. It also seems to be mainly holding The Restaurant Group, which is a publicly traded company that holds several restaurant franchises.

Additional information

Notes on contributors

Ludovic Phalippou

Ludovic Phalippou is professor of Financial Economics at the University of Oxford Said Business School, Oxford, UK.