Personalized Education

Advancing Education through Data Science, Machine Learning and Artificial Intelligence

Research Mission: Developing Machine Learning Methods for Enhancing Education

Different students have different abilities, backgrounds, interests, goals, needs and priorities, and so "one size" education does not fit all students. My research on personalized education is building and validating an artificial intelligence engine (e-Tutor) that creates a personalized plan of materials and study for a specific student in a specific course/setting, and also a recommended plan for subsequent courses/settings. The basis of e-Tutor is a novel multi-armed bandit scheme (staged bandits) that learns -- sequentially, over time -- how each specific student learns in a specific course/setting. Because e-Tutor is personalized to each student it is capable of evolving with the student. I believe this research represents a new, unique, important -- indeed, much-needed -- direction that is complementary to the current trend of global education as represented by MOOCs, online education, etc. which represent the embodiment of "one size" education. In parallel with e-Tutor I have used novel online clustering techniques to build tools that identify students (for instance, via grade prediction) who need help and additional attention -- perhaps by e-Tutor.

Learn more about our vision!

Principal investigator

  • Prof. Mihaela van der Schaar (Email)


  • J. Xu, Y. Han, D. Marcu, M. van der Schaar, "Progressive Prediction of Student Performance in College Programs," AAAI, 2017. [Link]
  • J. Xu, K. H. Moon, and M. van der Schaar, "A Machine Learning Approach for Tracking and Predicting Student Performance in Degree Programs, " accepted and to appear in IEEE Journal of Selected Topics in Signal Processing, 2017. [Link]
  • W. Whoiles and M. van der Schaar, "Bounded Off-Policy Evaluation with Missing Data for Course Recommendation and Curriculum Design, " ICML, 2016. [Link]
  • J. Xu, T. Xiang and M. van der Schaar, "Personalized Course Sequence Recommendations, " IEEE Transactions on Signal Processing, vol. 64, no. 20, pp. 5340-5352, Oct. 2016. [Link]
  • Y. Meier, J. Xu, O. Atan, and M. van der Schaar, "Predicting Grades," IEEE Transactions on Signal Processing, vol. 64, no. 4, pp. 959-972, Feb. 2016. [Link]
  • Y. Xiao, F Dorfler, and M. van der Schaar, "Incentive Design in Peer Review: Rating and Repeated Endogenous Matching," accepted and to appear in IEEE Transactions on Network Science and Engineering, 2016. [Link]
  • C. Tekin, O. Atan and M. van der Schaar, "Discover the Expert: Context-Adaptive Expert Selection for Medical Diagnosis," IEEE Transactions on Emerging Topics in Computing, vol. 3, no. 2, pp. 220-234, June 2015. [Link]
  • C.Tekin, J. Braun and M. van der Schaar, "eTutor: Online Learning for Personalized Education, " ICASSP, 2015. [Link]

  • Presentations

  • "Presentation at NIPS 2016 - Machine Learning for Education Workshop," , 2016. [Link]