Given a dataset of demographic, lifestyle, social and school related attributes of students, predict student performance. Data is available on Canvas.
Three scenarios of predictions will be considered: i) Classification with two levels (pass/fail); ii) Classification with five levels (from I - excellent to V - insufficient); iii) Regression, with a numeric output that ranges between 0 and 20.
G3 (final grade; numeric from 0 to 20)
Your work should include comparison between different machine-learning models (one of which must be linear, and at least 2 non-linear models). Consider different scenarios where you exclude G1 and G2 variables from your models.