The evolution of hedge fund performance using artificial intelligence in their processes over the past decade.

In a world where technology is supposed to bring us solutions and performance, hedge funds did not miss the opportunity of the arrival of artificial intelligence a decade ago to improve their processes and hopefully their performance. The literature on the subject is quite recent and only a few studies go into the subject in depth. The objective of this thesis is to answer the following question: “How has the performance and hedging ability of AI-based hedge funds evolved relative to the market over the past decade?” The methodology developed to answer this question consists of running performance analyses (risk-adjusted ratios, maximum drawdown) and a DCC-GARCH process to assess the conditional correlation between the market and the hedge funds using artificial intelligence. The results show impressive risk-adjusted performances relative to the market before the COVID-19 crisis, but mixed results since then.