Eric Benhamou
Papers
3
Total Citations
12
H-Index
2
About
Eric Benhamou is a researcher working at the intersection of quantitative finance and machine learning, with a particular focus on portfolio optimization and deep reinforcement learning. His most notable contribution bridges two traditionally separate worlds: the classical Markowitz mean-variance framework, long dominant in asset management, and modern deep reinforcement learning techniques. This work, presented at ICAPS 2020 and disseminated across multiple venues, challenges the prevailing reliance on traditional financial planning methods such as minimum variance, maximum diversification, and equal risk parity by demonstrating how reinforcement learning can complement or enhance these approaches. Accumulating over a dozen citations across its various iterations, the research has drawn attention from both the finance and machine learning communities, reflecting its interdisciplinary appeal. Benhamou's work speaks directly to practitioners in asset management who seek to incorporate cutting-edge AI techniques into portfolio construction workflows. His contributions position him as an emerging voice advocating for greater dialogue between quantitative finance professionals and the machine learning research community, helping to modernize how investment strategies are designed and evaluated in an increasingly data-driven landscape.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3