Project Title

PLUS - Personalized Learning Squared: Doubling Math Learning by Optimizing Tutoring from Training to Practice

Project Summary

High-impact tutoring is one of the most powerful ways to accelerate learning, but it’s costly and difficult to deliver widely. PLUS Tutoring bridges that gap by combining skilled human tutors, students’ existing math practice software, and AI-driven analytics to deliver targeted help during the school day. The platform continuously analyzes students’ practice data – things like problem accuracy, time on task, and engagement patterns – to identify who is struggling, why, and when they’re most likely to benefit from human support. By allocating tutors only to students and moments of greatest need, PLUS dramatically reduces the cost per student while preserving the one-on-one interaction that drives gains. The result is more timely, effective tutoring that boosts mastery and confidence for the students who need it most. The theory of change is simple: use data and AI to focus scarce human tutoring where it has the biggest impact, which scales high-quality tutoring across schools and improves equity in learning outcomes.

PLUS’ Impact

  • In a study of 110 students engaging in 12 weeks of tutoring, those who participated in goal-setting interventions increased their weekly math practice time by 25% and improved skill mastery by 40% compared to their baselines. Learn More.
  • Using a quasi-experimental difference-in-discontinuities design, 635 students were assigned to receive proactive or reactive tutoring during math practice using IXL. Results indicate that PLUS tutoring led to 43% greater growth on standardized tests compared to AI-only tutoring. Learn more.


What have teachers and students said about HAT?

  • Middle school teacher, “I love that PLUS Tutoring provides an opportunity for kids to have more help in the classroom. It’s not just me trying to get to every student but it’s more specific to their needs. I feel like they get a little bit more out of every day.”
  • Student, “Tutoring has helped me do more in math, I am able to understand it better.”


Media

or contact Shivang Gupta at shivang@cmu.edu

Team Members

Ken Koedinger
Professor of Human Computer Interaction and Psychology at Carnegie Mellon University
Shivang Gupta
Managing Director - PLUS at Carnegie Mellon University
Emma Brunskill
Associate Professor in the Computer Science Department at Stanford University
Danielle Thomas
Systems Scientist in the Human-Computer Interaction Institute within the School of Computer Science at Carnegie Mellon University
Lee Branstetter
Professor of Economics and Public Policy at Carnegie Mellon University
Vincent Aleven
Professor of Human-Computer Interaction & Director, Creating Adaptive Tutoring Systems (CATS) Lab