Marcos Lopez de Prado

Marcos Lopez de Prado holds two PhDs — one in financial economics from Universidad Complutense de Madrid and another in mathematical finance from Cornell University — and has held senior quantitative research roles at some of the most prominent investment firms in the world, including AQR Capital, Tudor Investment, and the Abu Dhabi Investment Authority. He is one of the most cited researchers in financial machine learning. His book "Advances in Financial Machine Learning" (Wiley, 2018) systematically addresses the specific challenges of applying ML techniques to financial time series — including the dangers of backtest overfitting, the proper way to build purged and embargoed cross-validation schemes for financial data, the construction of fractionally differentiated features, and the use of feature importance methods to avoid information leakage. The book became the standard reference for practitioners applying ML to quantitative investment and was the most-cited finance book of the 2018-2022 period. Lopez de Prado followed this with "Machine Learning for Asset Managers" (2020) and "Quantitative Portfolio Management" (2022). He is also known for work on hierarchical risk parity (HRP) — an alternative to mean-variance optimisation that uses hierarchical clustering to construct diversified portfolios without requiring matrix inversion. He is a recipient of the IAQF Financial Engineer of the Year award.