Amanda Coston is a PhD student in Machine Learning and Public Policy at Carnegie Mellon University (CMU). Her research considers fairness in algorithmic decision support systems. She is advised by Alexandra Chouldechova and Edward H. Kennedy.

Research projects

Her research considers the impact of algorithmic risk assessments in settings such as child welfare screening, criminal justice, and loan approvals. She is particularly interested in how techniques from causal inference and transfer learning can resolve current limitations of these systems. Her research focuses on questions of fairness. For more on current and past projects, please see Research.

Papers and Presentations

A. Coston, A. Mishler, E. H. Kennedy, and A. Chouldechova. "Counterfactual Risk Assessments, Evaluation, and Fairness." ACM FAT* 2020. arXiv:1909.00066

H. Zhao, A. Coston, T. Adel, & G. J. Gordon, (2019). Conditional learning of fair representations. ICLR 2020. arXiv:1910.07162

A. Coston, K. N. Ramamurthy, D. Wei, K. R. Varshney, S. Speakman, Z. Mustahsan, S. Chakraborty. "Fair Transfer Learning with Missing Protected Attributes," AAAI/ACM Conference on Artificial Intellligence, Ethics, and Society (AIES), 2019

A. Coston, L. Leqi. "Offline Heterogeneous Policy Evaluation: A Causal Approach," Causal ML workshop at ICML, 2018

She is involved in machine learning in the developing world, fairness, and AI for social good conferences.