Scholars@Duke

Funda Güneş obtained an M.S. and Ph.D. in Statistics from North Carolina State University in 2010, where her dissertation focused on confidence region-based tuning for regularized regression models. After graduation, she joined SAS Institute, where she held various positions from research statistician to principal machine learning developer. In her early years at SAS, she promoted new statistics modeling and estimation techniques to external statisticians and biostatisticians. This included writing technical papers, creating code examples, and giving expository talks and tutorials at analytics and academic conferences on mixed models, model selection, survival analysis, and Bayesian statistics.

In 2014, she transitioned into a machine learning developer and researcher position to research, design, implement, test, document, and maintain machine learning code for performing end-to-end analytics for predictive models. She implemented applied machine learning techniques, including stacked ensemble modeling, automated machine learning, model interpretability, and responsible AI for SAS’s modern in-memory cloud-based web interface, SAS Visual Data Mining, and Machine Learning. Funda holds a patent in automated machine learning, and she gave various talks about her work at nationally recognized academic conferences and meetings. 

Her research focuses on combining well-established statistical methods with an algorithmic approach to solve challenging predictive modeling and forecasting problems. More recently, she has been interested in health equity research focusing on Responsible AI and the intersection of causal inference and machine learning for analyzing large electronic health records data.

Funda is passionate about mentoring and advising students and supporting women in the data science community. As the Director of the Master’s Program at Duke, she teaches courses, mentors students, and prepares them for the next phase of their careers. This involves supporting students by collaborating with other organizations within the university and the outside industry by building partnerships with professional organizations and expanding opportunities for all students.

She is also co-founder of the North Carolina chapter of Women in Machine Learning and a data science committee member, where she promotes and supports women in the data science community by creating learning and networking opportunities through partnerships with leading companies and accomplished professionals. Also, she is a data science committee member for the Grace Hopper Celebration and a WiDS (Women in Data Science) ambassador.