Intro to Machine Learning Course Project, where we built machine learning algorithms to predict whether a student can correctly answer a specific diagnostic question based on the student’s previous answers to other questions and other students’ responses.
In part a we explored models such as K Nearest Neighbors, Item Response Theory, and Auto Encoders, as well as the effect of Ensemble technique.
In part b we improved model performance by extending Item Response Theory (IRT) to consider student demographics.
Details can found in final_report.pdf
Some of the source code belongs to CSC311 Course Team