Private equity (PE) has become an important component of investment portfolios across the globe. PE fund manager selection is one of, if not the, most important yet challenging decisions that investors in the PE asset class need to take. Historically, investors have relied on their experience and available quantitative information about the past success of the fund to tackle the challenge of fund manager selection within PE.
Researchers from SKEMA Business School have partnered with Unigestion, the University of Oxford, and the Technical University of Munich to examine for the first time the efficacy of combining machine learning (ML) algorithms and Natural Processing Language (NLP) techniques to predict the performance of PE funds.
Researchers trained AI models to identify high-performing PE funds by reading close to 400 fundraising prospectuses.
Surprisingly, the finding shows that PE fund performance is unrelated to quantitative information, such as prior performance, and measures of document readability. Meanwhile, AI tools can use qualitative information to predict future fund performance: the performance spread between the funds within the top and bottom terciles of predicted probability of success is about 25%.
These results show that Artificial Intelligence can help pick out top-performing PE funds better than many institutional investors. These findings support the view that in opaque and non-standardised markets, such as private equity, investors fail to incorporate qualitative information in their asset manager selection process.