Zequn Li 李泽群

PhD Candidate

Steven Institute of Technology

Biography

Zequn Li is a PhD Candidate at Stevens Institute of Technology. Her research focuses on empirical asset pricing and interpretable machine learning, particularly in understanding the dynamics between firm characteristics and stock returns. Looking ahead, Zequn is eager to expand her research into fintech and financial analytics, with a focus on applying innovative technologies to financial markets.

In addition to her research, Zequn is dedicated to teaching and mentoring students in finance and quantitative methods. She has extensive experience teaching courses in programming for finance, statistics, and stochastic calculus, where she emphasizes the practical application of these skills in the financial industry. Zequn’s teaching approach is designed to inspire students’ interests, guide them in discovering their academic and professional goals, and equip them with the technical expertise needed to excel in their careers.

Interests

Empirical Asset Pricing
Interpretable Machine Learning
Fintech
Financial Analytics

Education

PhD in Financial Engineering, Expected 2025
Stevens Institute of Technology
M.Sc in Financial Engineering, 2018
NYU Tandon School of Engineering
BSc in Finance and Applied Math, 2016
University of Rhode Island
BSc in International Finance, 2016
中南财经政法大学

Skills

Technical

Python

SQL

Hobbies

Skiing

Dogs

Travel

Working Papers

Zequn Li, Xiaoxia Lou, Ying Wu, Steve Yang

Apr 27, 2024

Interpreting Cross-Sectional Returns of Machine Learning Models - Firm Characteristics and Moderation Effect through LIME

Our study introduces a novel framework to interpret machine learning asset pricing models through the Local Interpretable Model-agnostic Explanations (LIME) method. This methodology illuminates how the inclusion of LIME local coefficients, representing the interaction among characteristics within ML models, modifies the relationship between a firm characteristic and stock returns.

Zequn Li

Apr 27, 2024

Interpreting Characteristics Behaviors In Empirical Asset Pricing

This study introduces an innovative framework to interpret the behaviors of firm characteristics in predicting expected returns through machine learning models, directly addressing the challenges of transparency and interpretability. Our approach utilizes the Local Interpretable Model-Agnostic Explanations (LIME) to evaluate firm characteristics based on their statistical significance and behaviors—linearity, independence, insignificance, and interaction—offering a novel perspective on their predictive roles.