Model performance

machine_learning

#1


1:What does ‘predictors’ mean here??? What is the use of it???

From cv_score to rmse values how can you say that it is better than the baseline model?? How can you say that it signifies over fitting???


#2

By looking at the first picture, I believe the predictors are the independent variables. Here a function modelfit is defined where dtrain[predictors] represent the features and dtrain[target] is the target variable.

Secondly, I want to know if you are familiar with the concept of overfitting? Since some features have a very high coefficient value, the model is overfitting on these variables.


#3

Not that much … is there any av article on over fitting??