About the Project
This is a joint research project between Stanford and TAL aiming to develop adatpvie assessment and curriculum based on a large amount of real educational data.
Project Goal
-
Develop better models to predict students’ answers to questions based on their previous actions andresponses.
-
Given effective knowledge tracing algorithms, devising ways to build models upon them to sequence material in ways maximally useful for students.
-
To use the text of questions and answers to perform natural-language analysis and experiment with augmenting knowledge-tracing and other algorithms to be able to incorporate new questions (which were not included in training data) into the software.
-
Use official score reports to study to what degree it is possible to predict students’ real test scores based on their interactions with the software.
Dataset
Real students’ GMAT practice records and test scores. We will opensource the dataset in future.
Contact
Sherry Ruan: ssruan@stanford.edu
Alex Kolchinski: kolchinski@stanford.edu