maryann_gray Can students use the OPEID number in there code? Students state it is increasing the r-squared. Doesn't seem logical to use the OPEID number, is this happening by chance?
dylarm maryann_gray It's not by chance, it's because OPEID is unique to each university. So including it basically makes the model regurgitate the original values (see Dash's explanation about the same thing regarding including "city" here). In Notebook 4 it's also likely to cause issues when dealing with the training vs testing data sets.
![After The AP Data Science Challenge [Teacher Forum]](https://dschallengeteachers.freeflarum.com/assets/logo-024smqgu.png){kind=logo}