We unite multiple disciplines - machine learning, learning design, evidence and impact evaluation - to understand why students struggle, then build the tools and infrastructure our partners need to help them to succeed.
Eedi has earned two gold EDUEvidence certificates. The Efficacy certificate for demonstrating statistically significant impact through randomised controlled trials (RCTs). The Effectiveness certificate for demonstrating that teachers were able to implement Eedi School in their own classrooms, with limited external support. These RCTs were independently verified by What Works Education, a UK-based evaluator.
Our research is driven by three collaborative, interdisciplinary teams.
Our Evidence & Impact team puts our impact to the test. We design and execute gold-standard Randomised Controlled Trials (RCTs) that generate robust evidence of real and measurable learning gains.
Our Data Science team builds the sophisticated models that power our diagnostic engine. They translate academic research and real-world data into the predictive, practical AI that underpins our entire ecosystem, from classroom-based research tools to large-scale diagnostic engines.
Our Learning Science team maps the landscape of human knowledge. They architect our knowledge graphs, design our innovative diagnostic items, and ensure our AI is grounded in a deep, evidence-based understanding of how students actually learn.
Four core principles guice our approach to building the future of learning.
We believe innovation starts by solving real problems for teachers. We develop accessible, low tech, easy-to-use tools like DQR, which turns a single smartphone into a classroom-wide diagnostic. These insights and data fuel the sophisticated models that power our BUILD and LEARN infrastructure, ensuring our technology is always grounded in classroom reality.
True progress in education requires moving beyond a simple measurement of right and wrong answers to understanding why a student gets stuck. Through our uniquely designed diagnostic items and inference models, we identify the specific misconceptions tht block learning and allow our partners to deliver precise and effective interventions.
The greatest challenges in education demand a collective effort. We actively partner with the world's leading academic and industry labs, including Google DeepMind and the University of Cambridge, to advance the frontier of our field. We are committed to sharing what we learn, contributing to peer-reviewed science, and open-sourcing key parts of our infrastructure to lift the entire Learning Engineering field.
We believe the benefits of advanced technology should not be reserved for the well-resourced but should positively impact every student equally.
Low tech tools, like our DQR solution, turn a simple smartphone and printed QR cards into a powerful assessment tool, bringing the benefits of real-time diagnostic insights to teachers and classrooms across the world.
Eedi is an education impact lab that partners regularly with other world class organizations
![[headshot] image of customer (for a bars & pub)](https://cdn.prod.website-files.com/68b00fd42843f377c633738c/68fb94f0a2f2c13a45ccf5f9_Andrew%20Lan.webp)
Eedi is the GOAT of sharing data with researchers and enabling new development in AI for education.
![[headshot] image of customer (for a financial advisor)](https://cdn.prod.website-files.com/68b00fd42843f377c633738c/68fb95f6f14a7d81713a485e_Scott%20Crossley.webp)
Eedi helps students advance in math by working closely with leading researchers and academic institutions to develop evidence-based approaches to understanding misconception. Their focus on data-driven methods, data collaborations, and large-scale human sourced analytic solutions to pressing educational concerns provides them unique capital to succeed.
![[headshot] image of customer (for a real estate tech)](https://cdn.prod.website-files.com/68b00fd42843f377c633738c/68fb948e9904b4b168556880_Rene.webp)
Eedi has been an outstanding research partner and catalyst for advancing the science of teaching and learning. They routinely partner with leading education researchers to advance evidence-based practices. I have collaborated with Eedi for several years — their commitment to open science is exemplary.
![[headshot] image of customer (for a construction company)](https://cdn.prod.website-files.com/68b00fd42843f377c633738c/68fb955151a56c51af260b57_mihaela.webp)
Our lab has been pioneering AI for education for over a decade, guided by a central goal: AI for human empowerment. Our collaboration with Eedi advances that mission, making learning more personal and accessible for everyone.
A sample of published research using Eedi data.
In 2020 we hosted the NeurIPS Education Challenge to predict student responses, determine question quality, and identify a personalised set of questions for each student. 3696 entries were received from 382 teams.
In 2021, the data set we released won the Educational Data Mining Society's Best Publicly Available Educational Data Set Prize.
A follow-up challenge at NeurIPS in 2022 involved the exploration of how causal relationships between constructs and inference impact learning. Our dataset includes real-world AB experiment data which can be used for evaluating causal models.
Looking to empower teachers, build a smarter learning platform, or co-author the future of AI tutoring?
