Skip navigation
Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp013n204212c
Title: Understanding and Benchmarking Private Equity via Factor Risk Analysis
Authors: Chen, Dionne
Advisors: Mulvey, John
Department: Operations Research and Financial Engineering
Class Year: 2020
Abstract: For decades, private equity investment has been hailed by institutional investors for its impressive returns and diversifying effect within a portfolio of investments. However, recent empirical evidence may indicate shifting tides in the market as the onslaught of available capital may be creating an increasingly competitive marketplace. In order to better understand and hedge the shifting marketplace, this thesis seeks to construct a benchmark for private equity that is both fully investible and an appropriate instrument for comparison. First, we estimate a factor model on private equity returns to understand the risk factors driving its performance. We follow the methodology proposed in Franzoni et al. (2011) to estimate a factor model from cash flows, and augment the model with a LASSO regularization term. The estimation finds that private equity returns are significantly driven by exposure to stock market risk, and partially driven by the Fama French Small Minus Big (SMB) and High Minus Low (HML) factors. Following the insights from the factor estimation, we construct a leveraged portfolio of small-cap, value stocks with long holding periods as a passive replicating strategy. We test the benchmark against aggregate private equity performance and find that the replicating portfolio is vastly superior to the S&P 500 as a passive and investible benchmark of the private equity industry.
URI: http://arks.princeton.edu/ark:/88435/dsp013n204212c
Type of Material: Princeton University Senior Theses
Language: en
Appears in Collections:Operations Research and Financial Engineering, 2000-2023

Files in This Item:
File Description SizeFormat 
CHEN-DIONNE-THESIS.pdf942.85 kBAdobe PDF    Request a copy


Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.