Papers
1
Total Citations
14
H-Index
1
About
Shi Ming Yu is a rising scholar at the intersection of machine learning, optimization, and behavioral finance. Their research centers on developing computational methods to infer human decision-making patterns from observed data, with a particular emphasis on risk preferences and portfolio choice. Yu’s most-cited work, "Learning risk preferences from investment portfolios using inverse optimization" (2023, 14 citations), introduces a novel framework that reverses traditional optimization: instead of prescribing optimal portfolios, it uses observed investment choices to reverse-engineer an investor’s underlying risk attitudes. This contribution is significant because it bridges the gap between normative financial theory and actual investor behavior, offering a data-driven tool for personalized financial advice and robo-advisory systems. By applying inverse optimization techniques—a field more common in engineering—to finance, Yu opens new avenues for understanding how people truly make decisions under uncertainty. Their work has already garnered attention for its practical implications in wealth management and behavioral economics. As an emerging voice in computational finance, Shi Ming Yu is poised to shape how we model and respond to real-world investment behavior.
Research Focus
Key Achievements
Top Papers
- 1