Yi Ding
About Yi Ding
Yi Ding serves as the Sr Director and Head of Decision Science and Modeling at Sallie Mae, where he has worked since 2018. With over 18 years of experience in credit risk and marketing modeling, he specializes in machine learning techniques and statistical predictive modeling within the banking industry.
Work at Sallie Mae
Yi Ding has served as the Senior Director and Head of Decision Science and Modeling at Sallie Mae since 2018. In this role, he leads the development of machine learning models for the company's student loan and credit card portfolios. His work involves utilizing advanced techniques such as Gradient Boosting, K-Nearest Neighbors (KNN), and text mining, primarily leveraging AWS for model deployment. His leadership in decision science focuses on enhancing credit risk and marketing modeling strategies within the organization.
Education and Expertise
Yi Ding holds a Master’s Degree in Computer Science and a Master’s Degree in Operations Research & Industrial Engineering from North Carolina State University. He is also a PhD candidate (ABD) in the same field. His educational background provides a strong foundation for his expertise in statistical predictive modeling techniques, including regressions, decision trees, survival analysis, and time series analysis. He specializes in stress testing and Current Expected Credit Loss (CECL) models, particularly in the finance cash flow engine domain.
Background in Banking Industry
With over 18 years of experience in the banking industry, Yi Ding has a robust background in credit risk and marketing modeling. Prior to his current position at Sallie Mae, he worked at JPMorgan Chase & Co. as a Vice President and Senior Risk Manager in Core Modeling from 2013 to 2018. He also served as a Senior Risk Analyst at JPMorgan Chase from 2006 to 2011. His earlier experience includes a role as a Risk Analyst at HSBC Card Services and as a Quantitative Modeling Manager at Bank of America.
Technical Skills and Methodologies
Yi Ding employs advanced machine learning techniques in his work, utilizing tools such as Python and AWS. His technical skill set includes proficiency in Gradient Boosting, Neural Networks, and Bayesian methods. He leads the development of various machine learning models, including xgboost and KNN, which are essential for analyzing and improving credit risk assessments and marketing strategies in the financial sector.