Assistant Professor of Operations & Technology Management
Questrom School of Business, Boston University
PhD in Operations Research
Massachusetts Institute of Technology
Research Interests:
▪ Trustworthy AI & Machine Learning
▪ Healthcare & Sustainability
▪ Optimization
Address: 595 Commonwealth Avenue, Boston, MA 02215
Contact: vvdigalakis [at] gmail [dot] com
I am an Assistant Professor of Operations & Technology Management at the O&T Management Department at Boston University's Questrom School of Business. I completed my Ph.D. in Operations Research at the Operations Research Center at MIT in 2023, advised by Prof. Dimitris Bertsimas. My journey has also included HEC Paris, France, where I spent 2 years as an Assistant Professor, the Alexa Natural Language Understanding team at Amazon Science, and the Technical University of Crete (TUC), Greece, where I completed my Diploma in Electrical and Computer Engineering.
Find my CV here.
Research. I develop methods in trustworthy AI and machine learning, with applications in healthcare and sustainability. My work aims to make data-driven decision-making interpretable, robust and stable, private and secure, and fair — which is critical for its adoption in high-stakes environments. Read about a selection of projects below.
🧩 Can machine learning models remain stable and consistent as they retrain on new data?
Yes—if we design them that way. In collaboration with a major U.S. hospital system, we built interpretable ML models, such as decision trees, that are structurally stable upon retraining. This improves reliability and trust in clinical deployment.
Slowly Varying Regression under Sparsity (with D. Bertsimas, M. Li, O. Skali Lami). Operations Research, 2024.
Improving Stability in Decision Tree Models (with D. Bertsimas).
Towards Stable ML Model Retraining via Slowly Varying Sequences (with D. Bertsimas, Y. Ma, P. Paschalidis).
🌱 How can industry invest in renewables under deep climate uncertainty?
By planning for the worst, not just the average. In partnership with OCP—the world’s largest phosphate producer—we developed a machine learning- and robust optimization-based framework guiding a $2 billion investment in solar and batteries to decarbonize fertilizer production.
Decarbonizing OCP (with D. Bertsimas, R. Cory-Wright). M&SOM, 2024.
Selected as the 2023 M&SOM Practice-Based Research Competition Finalist
💉 Can we allocate vaccines fairly during a pandemic?
... or, more broadly, can we distribute resources fairly among states and sub-populations to ensure equity? Partnering with FEMA during COVID-19, we designed an equity-aware allocation predictive and prescriptive model for placing mass vaccination centers and distributing vaccines across states.
Where to locate COVID-19 mass vaccination facilities? (with D. Bertsimas, A. Jacquillat, M. Li, A. Previero). Naval Research Logistics, 2021.
Won the 2024 Harold Kuhn Award
Find out more about my research.
I am interested and have worked on all dimensions of trustworthy AI—interpretability and explainability, stability and robustness, fairness, and privacy. Leveraging the rich modeling power of optimization paradigms such as mixed-integer, robust, and multi-objective optimization, I focus on developing models that incorporate trustworthiness considerations a priori and on understanding, evaluating, and navigating the trade-offs among the components of trustworthy analytics a posteriori.
My research has been published in journals such as Operations Research and Manufacturing & Service Operations Management, and has received awards, including the and the 2021 INFORMS Pierskalla Award. For a full list of publications and preprints, please visit my Google Scholar page — or read below.
Slowly Varying Regression under Sparsity (with D. Bertsimas, M. Li, O. Skali Lami). Operations Research, 2024.
Improving Stability in Decision Tree Models (with D. Bertsimas). 2023.
Towards Stable ML Model Retraining via Slowly Varying Sequences (with D. Bertsimas, Y. Ma, P. Paschalidis). 2024.
Decarbonizing OCP (with D. Bertsimas, R. Cory-Wright). M&SOM, 2024.
The backbone method for ultra‐high dimensional sparse machine learning (with D. Bertsimas). Machine Learning, 2022.
BackboneLearn: A Python Library for Scaling Interpretable Mixed-Integer Optimization-Based Machine Learning (with C. Ziakas). 2024.
Frequency Estimation in Data Streams: Learning the Optimal Hashing Scheme (with D. Bertsimas). IEEE TKDE, 2022.
Where to locate COVID-19 mass vaccination facilities? (with D. Bertsimas, A. Jacquillat, M. Li, A. Previero). Naval Research Logistics, 2021.
Improved Pan-Private Stream Density Estimation (with G. Karystinos, M. Garofalakis). 2021.
Data Analytics with Differential Privacy. Diploma Thesis, 2018.
From predictions to prescriptions: A data-driven response to COVID-19 (with D. Bertsimas et al). Health Care Management Science, 2021.
Figure: List of 20 most common keywords from my first 10 papers
[FOR STUDENTS] To work with me as an MSc/PhD student or as a research assistant, please complete this Google form.
Teaching. I have taught and developed courses in sustainable operations management (Operations and Supply Chain Management, HEC Paris), analytics and machine learning (Interpretability and Algorithmic Fairness, HEC Paris; Machine Learning under a Modern Optimization Lens, MIT; The Analytics Edge, MIT), optimization (Robust Modeling, Optimization, and Computation, MIT), computing (Computing in Optimization and Statistics, MIT), and introductory mathematics (Mathematics I, TUC) at various levels (PhD, MSc, MBA, undergraduate) and backgrounds (data science, engineering, business, business law).
