
In this episode of Capital Allocators, host Ted Seides interviews Daniel Mahr, head of MDT, a quantitative equity investing group at Federated Hermes. Mahr discusses his early experiences with IPOs, which shaped his appreciation for disciplined investing, and traces the evolution of MDT's strategies from traditional factor tilting to a decision tree approach using machine learning. He emphasizes the importance of transparency in their "glass box" approach, balancing analytical rigor with human judgment, and shares insights on avoiding overfitting and underfitting data. Mahr also touches on the challenges of team building in a competitive market for data science talent and the excitement of continuously adapting to the ever-evolving financial markets.
Sign in to continue reading, translating and more.
Continue