Research (By Topic)

My current research centers around (1) machine learning algorithms, (2) data-driven social good, and (3) the human-AI interface.

Machine Learning Algorithms

I primarily study the design and analysis of transfer learning and bandit algorithms for effective data-driven decision-making.
Applications include personalized healthcare, clinical trial designs, dynamic pricing and product recommendations.

Adaptive Clinical Trial Designs with Surrogates: When Should We Bother?
A. Anderer, H. Bastani and J. Silberholz
Major revision, Management Science
Winner, Pierskalla Award for Best Paper in Healthcare (2019)

Meta Dynamic Pricing: Transfer Learning Across Experiments
H. Bastani, D. Simchi-Levi and R. Zhu
Minor revision, Management Science

Learning Personalized Product Recommendations with Customer Disengagement
H. Bastani, P. Harsha, G. Perakis and D. Singhvi
Major revision, M&SOM
Second Place, Service Science Best Paper Award (2019)

Predicting with Proxies: Transfer Learning in High Dimension
H. Bastani
Management Science (forthcoming)

Mostly Exploration-Free Algorithms for Contextual Bandits
H. Bastani, M. Bayati and K. Khosravi
Management Science (forthcoming) [open-source code]

Online Decision-Making with High-Dimensional Covariates
H. Bastani and M. Bayati
Operations Research, 68 (1), 276-294 (2020)
Winner of Pierskalla Award for Best Paper in Healthcare (2016), George Nicholson Student Paper Competition (2016),
MSOM Student Paper Competition (2016), and IBM Service Science Best Student Paper Award (2016)

Data-Driven Social Good

I am passionate about using novel sources of data to better enable socially responsible operations and healthcare policy.

Responsible Sourcing: The First Step is the Hardest
P. Ramchandani, H. Bastani and K. Moon
People's Choice Award, Early-Career Sustainable OM Workshop (2020)

Do Policies with Limited Enforcement Reduce Harm? Evidence from Transshipment Bans
H. Bastani and J. F. de Zegher
Major revision, Management Science
People's Choice Award, Early-Career Sustainable OM Workshop (2019)

Evidence of Upcoding in Pay-for-Performance Programs
H. Bastani, J. Goh and M. Bayati
Management Science, 65 (3), 1042-1060 (2019)
Winner, Health Applications Society Best Student Paper Award (2015)
News coverage: Science Daily

Analysis of Medicare Pay-for-Performance Contracts
H. Bastani, M. Bayati, M. Braverman, R. Gummadi, and R. Johari

Human-AI Interface

I am excited about developing methods for integrating insights from machine learning models into human workflows.

Learning Best Practices: Can Machine Learning Improve Human Decision-Making?
H. Bastani, O. Bastani and P. Sinchaisri

Proceed with Care: Integrating Predictive Analytics with Patient Decision-Making (draft)
H. Bastani and P. Shi
Invited book chapter for Modeling for Health: Making Changes (edited by S. Suen, E. Enns and D. Scheinker)

Interpreting Predictive Models for Human-in-the-Loop Analytics
O. Bastani, C. Kim and H. Bastani
Preliminary version in FATML (2017)
Finalist, Pierskalla Award for Best Paper in Healthcare (2018)
News coverage: New York Times, Sloan Management Review


In my past life, I used to work on experimental optics research.

Creating Optical Vortex Modes with a Single Cylinder Lens
H. Sridhar, M. Cohen and J. Noe
Proc. SPIE (2010)

Multiplex coherent anti-Stokes Raman scattering (MCARS) for chemically sensitive, label-free flow cytometry
C. Camp, S. Yegnanarayanan, A. Eftekhar, H. Sridhar and A. Adibi
Optics Express (2009)