2021-2022 Winner

Watch a Demo Video:

Scalable Methods for Customized Digital Learning

A toolkit that enables developers to create personalized in-app student experiences and guide teachers to track progress

United States of America
Track:
Learning Science Research
Award Level:
Growth Award

Project Description

Scalable Methods for Customized Digital Learning is a toolkit that provides education application developers with algorithms for assessment of student proficiency. Precise assessment of students’ strengths and weaknesses makes it possible to customize learning modules, find the right balance between easy and difficult materials, and substantially improve learning outcomes. These algorithms will make this type of personalization possible, and the accompanying toolkit includes notebooks that guide developers through comparing methods, evaluating performance, and creating teacher dashboards.

Meet Our Team

Susan Athey

Professor, Stanford Graduate School of Business

Ayush Kanodia

Fourth year PhD Student in Computer Science, Stanford University

Phase III results for the Building an Adaptive & Competitive Workforce track will be released in late May. Meet the finalists for all other tracks here.