Please enable JavaScript.
Coggle requires JavaScript to display documents.
Ch 17: evaluate model performance (ROC curve (Receiver Operating…
Ch 17: evaluate model performance
understanding model performance
a models business context
Fraction of Variance Explained (FVE) Binomial
how much variance has been explained/how far off
decision tree
takes most predictive feature and splits the data
Find the most predictive feature (the one that best explains the
target) and place it at the root of the tree
Split the feature into two groups at the point of the feature where the two groups are as homogenous as possible
repeats for each predictive feature
ROC curve
Receiver Operating Characteristics
orange
validation
cross validation
prediction description
confusion matrix
true negative
false negative
true positive
false positive
area under curve
lift chart for business decisions
sorting all validation cases by probability of readmission
creating diagrams