MathE is an adaptive mathematics learning tool. When students log in to the training area of mathE, they choose a topic to study and specify whether they prefer basic or advanced questions. The platform then selects a set of seven multiple-choice questions based on their preference and generates a test for the student. After completing and submitting the test, the answers are recorded and stored. My dataset consists of 9546 answers to 833 questions provided by 372 students from 8 countries who have used the platform.

My task is to predict whether a question will be answered correctly or not given the student, country, question, difficulty, topic, etc.

References: MathE Platform: https://mathe.ipb.pt/homePage Abstract on Dataset Contents: https://pubmed.ncbi.nlm.nih.gov/38445202/ Dataset Download: https://archive.ics.uci.edu/dataset/1031/dataset+for+assessing+mathematics+learning+in+higher+education

I have included my trial and error results to help demonstrate my thought process despite not being polished for presentation

While none of the models developed were exceptionally powerful, they perform significantly better than chance and provide interesting insight into the provided data! Read the conclusion in the notebook for more details.