Theja Tulabandhula

Researcher in Artificial Intelligence & Applied Machine Learning


I work on developing new machine learning and optimization methods in applications that typically interface with people, such as retail and next-generation transportation. My current and prior work experiences include working with/at the University of Illinois at Chicago, Xerox Research, Massachusetts Institute of Technology, Citadel Investments, Apple, State Street Global Advisors, and Texas Instruments to name a few.

You can visit DBLP, Arxiv, SSRN or Google Scholar to see some of the research threads I have pursued (some presentations are also available on youtube).

Some examples research outcomes are:

  • Enhancing supervised learning in the presence of operational information
  • Solving transportation problems such as scheduling, crowdshipping and enabling fair ride-shares
  • Optimizing and personalizing recommendations and prices assuming realistic user behavior models
  • Product pricing and learning in economic and competitive settings (e.g., capturing loyalty)
  • Designing theoretically well-behaved online and reinforcement learning methods for applications involving personalization by exploiting the underlying application specific structure.


  • PhD in Electrical Engineering and Computer Science (thesis topic area: Machine Learning and Optimization), 2014,  Massachusetts Institute of Technology, Cambridge, USA.
  • Dual Degree in Electrical Engineering (Prime Minister’s Gold Medal for being ranked 1 GPA-wise across the university), 2009,  Indian Institute of Technology Kharagpur, India.

Current Interests

I am broadly interested in pursuing practical solutions to applied problems, which make use of the right set of statistical models and data driven decision making methods, and have a significant impact on business and societal outcomes.

Specific interests include:

  • Modeling human behavior and enhancing their decision making prowess quantitatively
  • Developing application specific machine learning/statistical methods
  • Developing special-purpose optimization and reinforcement learning methods for real life deployment
  • Tech entrepreneurship (e.g., ML Ops: see my recent course playlist)