Associate Director of the IDEA, Mathematical Sciences
Dr. Bennett brings over 30 years of research experience in artificial intelligence, machine learning, and their applications to problems in health, science, and industry. Her research specialty is working with people with problems and data and then developing novel machine learning and AI models and work flows to solve their problems. She serves as Associate Director of Institute of Data Exploration and Applications (IDEA). Her role is to both lead major data science research projects, develop and lead teams for new research projects, and create data science research education programs. Her work with industry includes projects with GE (PI) and Global Foundries (co-Pi). She have been PI or Co-Pi on many data science research projects funded by GE (PI), Global Foundries (co-PI), Albany Capital District Physicians Health Plan (HMO, PI), IBM (co-PI), United Health Foundation/OPTUM Labs (PI), HBI Solutions (Healthcare Data Science, PI), Albany Medical Center (Hospital, PI), Bill and Melinda Gates Foundation (co-PI), NIH (PI and co-PI) and NSF (PI and co-PI). She has worked with electronic medical records and public health data to develop solutions to problems such as Treatment Effect Estimation, Emergency Department Readmission, Critical Care Management, and High Cost Medicare Patients. She works in emerging research areas such as health equity, ML fairness, and synthetic health data. She has been program chair and area chair, PC member and/or organizer for conferences in machine learning, data mining, and operations research including KDD, AAAI, Intl. Conf. on Continuous Optimization, International Conference on Machine Learning, NIPS, IEEE Conf. on Data Mining, COLT, INFORMS, and SIAM ICDM. She has over 130 research publications. She has been a plenary speaker at major conferences including AAAI, IJCNN, and IEEE BIBM. She founded and directs the Data INCITE Lab which does novel applied data analytics research. Data INCITE fully integrates education and research. Over 250 undergrad students have done research in Lab on real problems for actual clients resulting in publications and applications. Recent awards from her group include “MortalityMinder” https://mortalityminder.idea.rpi.edu which was a winner in the AHRQ Visualization of Social Determinants of Health Contest, 2019 and Best Student paper at ACM BCB 2021.
Ph.D., University of Wisconsin, Madison, 1993
M.S., University of Wisconsin, Madison, 1989
B.S., University of Puget Sound, 1985
- Machine Learning, Data Mining, Data Science
- Artificial Intelligence
- Combining operations research and artificial intelligence problem solving methods.
- Mathematical programming approaches to problems in artificial intelligence such as machine learning, neural networks, pattern recognition, and planning.
- Application of these techniques to medical, financial and scientific problems.
- Fairness and Equity in ML, AI and Health
- Innovative pedagogy in data analytics education.
- Bioinformatics and Cheminformatics
- R. Zhao, Md Ridwan Al Iqbal, K. Bennett and Q. Ji, “Wind Turbine Fault Prediction Using Soft Label SVM,” International Conference on Pattern Recognition (ICPR), 2016.
- J. Ryan, J. Hendler, and K. Bennett, “Understanding Emergency Department 72-hour Revisits Among Medicaid Patients Using Electronic Health Care Records”, Journal of Big Data, 3:4:238-248, 2015.
- Minoo Aminian, David Couvin, Amina Shabbeer, et al., “Predicting Mycobacterium tuberculosis Complex Clades Using Knowledge-Based Bayesian Networks,” BioMed Research International, Volume 2014 (2014), Article ID 398484, 11 pages http://dx.doi.org/10.1155/2014/398484
- A. Shabbeer, L. Cowan, J. Driscoll, C. Ozcaglar, S. L. Vandenberg, B. Yener, and K. P. Bennett, “TB-Lineage: an Online Tool for Classification and Analysis of Strains of Mycobacterium tuberculosis Complex”, Infection, Genetics and Evolution, 12:4, 789-97, 2012.
- T. Huang, J. Zaretzki, C. Bergeron, K. Bennett, C. Breneman, “DR-predictor: incorporating flexible docking with specialized electronic reactivity and machine learning techniques to predict CYP-mediated sites of metabolism”, Jnl. of Chemical Information and Modeling, 53:12: 3352-3366, 2013.
- J. Zaretzki, C. Bergeron, P. Rydberg, T.-W. Huang, K. P. Bennett, and C. Breneman, "RS-Predictor: A new tool for generating and validating models capable of predicting sites of cytochrome P450-mediated metabolism", Journal of Chemical Information and Modeling, 2011
- Andrew Yale, Saloni Dash, Ritik Dutta, Isabelle Guyon, Adrien Pavao, and Kristin P. Bennett, “Generation and Evaluation of Privacy Preserving Synthetic Health Data”, Neurocomputing, 416:244-255, 2020. DOI: https://doi.org/10.1016/j.neucom.2019.12.136.
- Kristin Bennett, Elisabeth Brown, Hannah De los Santos, Matthew Poegel. Thomas Kiehl, Evan Patton, Spencer Norris , Sally Temple , John Erickson, Deborah McGuinness, and Nathan Boles, “Identifying Windows of Susceptibility by Temporal Gene Analysis”, Scientific Reports - Nature, 2740, 2019.