Sandrine Ungari
Papers
3
Total Citations
12
H-Index
2
About
Sandrine Ungari is a quantitative researcher whose work sits at the dynamic intersection of financial optimization and machine learning, with a particular focus on portfolio construction and asset management. Her most recognized contribution, "Bridging the Gap Between Markowitz Planning and Deep Reinforcement Learning" (2020), represents a pioneering effort to reconcile two historically separate communities: traditional financial practitioners relying on classical risk-planning frameworks — such as Markowitz efficient frontier, minimum variance, and equal risk parity — and the emerging machine learning community advancing deep reinforcement learning techniques. By synthesizing these paradigms, Ungari's research opens new pathways for more adaptive, data-driven portfolio management strategies that retain the interpretability and rigor of established financial theory. The work has accumulated citations across multiple presentation and publication formats, reflecting its resonance within both the quantitative finance and artificial intelligence communities. Presented at ICAPS 2020, her research signals a broader movement within asset management toward integrating reinforcement learning as a practical complement to conventional optimization methods. For students and researchers exploring the frontiers of algorithmic investing and financial AI, Ungari's work offers a compelling and accessible bridge between two powerful but previously siloed disciplines.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3