In a world full of information, data science can help students who don’t have access to personalized learning. Knowledge Tracing means modeling of student knowledge over time. The goal is to accurately predict how students will perform on future interactions. These algorithms can be used to make presonalized online learning possible to every sudent with an internet connection.
Riiid's EdNet data is used for the task. EdNet is the world’s largest open database for AI education containing more than 100 million student interactions. It has data of around 1 million students.
The Feature importance as calculated by LightGBM
This project was made as a part of Riiid! Answer Correctness Prediction, a Code Competition at Kaggle. The task was given by Riiid Labs