Devavrat Shah

Devavrat Shah is a Professor at the Massachusetts Institute of Technology (MIT), affiliated with the Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Laboratory for Information and Decision Systems (LIDS). His research focuses on machine learning, causal inference, and algorithmic fairness, with applications in healthcare outcomes, criminal justice reform, and cryptocurrency analysis. He has contributed to groundbreaking work, such as developing a machine-learning algorithm that nearly doubled Bitcoin investments over 50 days using real-time price data analysis.

Shah's academic work integrates statistical methods with real-world challenges, including personalized medicine, policy evaluation, and bias detection in algorithms. His recent projects include global clinical studies on lymphoma treatments and frameworks for auditing racial bias in law enforcement systems. His interdisciplinary approach bridges computer science, statistics, and domain-specific applications.

Key areas of his research include causal inference frameworks for data-rich environments, algorithmic fairness in decision-making systems, and predictive modeling for healthcare and public policy. His work often combines theoretical rigor with practical impact, addressing societal challenges through data-driven solutions.

Shah's contributions to synthetic interventions and causal simulators have advanced trace-driven simulation methodologies, while his collaboration with global consortia like PETAL highlights his commitment to translational research. His students, including Kang Zhang, have contributed to impactful projects in algorithm design and data science.