Lingzhi(lenz) Du
About Lingzhi(lenz) Du
Lingzhi (Lenz) Du is the Director of Data Science at Zest AI, specializing in machine learning and credit risk modeling.
Company
Lingzhi (lenz) Du is currently associated with Zest AI, a company known for its innovative work in transforming the credit underwriting industry through the application of transparent machine learning (ML) solutions. Zest AI focuses on improving risk modeling to make credit scoring fairer and more accurate.
Title and Role
Lingzhi (lenz) Du serves as the Director of Data Science at Zest AI, where he leads the machine learning engineering effort. In this role, he focuses on developing cutting-edge solutions for credit risk modeling, predictive modeling, and model explainability. His work ensures the integration of transparent and explainable ML models into credit underwriting processes.
Education and Expertise
Lingzhi (lenz) Du holds two Master of Science degrees, one from the University of San Francisco in Data Science and another from the National University of Singapore in Statistics. He also earned a Bachelor of Science degree from Sun Yat-Sen University. His areas of expertise include credit risk modeling, predictive modeling, time series forecasting, deep learning, distributed computing, data visualization, model explainability, and model monitoring.
Professional Background
Prior to his current role at Zest AI, Lingzhi (lenz) Du has held several positions within the company, including Lead Data Scientist and Senior Data Scientist. Between these roles, he accumulated over three years of experience at Zest AI across various capacities. He also gained valuable experience as a Data Science Intern at Ubisoft, where he worked for seven months in San Francisco, CA.
Industry Contributions
Lingzhi (lenz) Du has made significant contributions to the field of data science, particularly in the development of machine learning platforms and solutions for credit underwriting. His work in model explainability and credit risk modeling is vital for creating fair and transparent credit scoring systems that can be easily understood and trusted by stakeholders.