Riiid LEADS THE ERA OF AI EDUCATION
AI research with real-world impact
Riiid focuses on AI research with the aim to maximize the learning outcome, and verifies its impact by fast commercializing the product. With innovative research for real-world uses, Riiid is changing the landscape of AI-based education.
TOEIC Learning Data
Average Score Increase on 20 Hours of Learning
Predicted Score Accuracy
Drop Out Prediction
Analyzing a relatively short session-based mobile learning environment, Riiid developed a deep learning Transformer-based predictive model called Deep Attentive Study Session Description. The model defines the concept of user ‘dropout’ for the first time and accurately predicts dropout rates by examining various learning behaviors of users.
Riiid apply the Transformer deep-learning model, mainly used in natural language processing, to Knowledge Tracing, one of the most fundamental tasks in AI education. Given the history of how a user responded to mock test questions, our AI model calculates and predicts the probability of the user giving either correct or incorrect answers.
Riiid proposes a deep learning Transformer-based assessment model to improve predictive accuracy with sparse data. A model is developed that pre-trains a user’s probability in making correct/incorrect answers and in-time problem solving. The model is then fine-tuned to match score predictions based on small amounts of score data.
Largest-scale Hierarchical Dataset in Education
Riiid has released the largest publicly available AI education dataset through a data platform called ‘EdNet’. EdNet is composed of 131,441,538 interactions collected from 784,309 students using our TOEIC PREP service since 2017. EdNet aims to encourage EdTech development and advance the AI education industry as a whole.