Code and report for a final project for the MIT 15.077 spring 2015 course (Statistical Learning and Data Mining)

NOTE: the files are meant to be run using RStudio (2015 version). If you run them in a different way, please make sure you change the relevants paths accordingly (in particular to load the input file).

---

ABBREVIATIONS used in the file names:

pf: pass or fail

class: grade classification

risk: identifying student at risk of dropping out of school

eg: exact grade

---

The data can be obtained here and the corresponding paper by Cortez and Silva (2008) here.

I have also written a post about the same case study with additional insights on my blog.