Please enable JavaScript.
Coggle requires JavaScript to display documents.
Chapet 17 (Using the Lift Chart For Business Decisions (Click "Lift…
Chapet 17
Using the Lift Chart For Business Decisions
Click "Lift Chart"
Constructed by sorting all validation cases by their probability of readmission
Ideal= Blue and Orange Lines are overlapping
Enable Drill Down
Allows you to download predictions to better understand model
Introduction
Fraction of Variance Explained (FVE) Binomial
Reasonable measure of how far from the target predictions are from the model
Shows how much variance there is in the model
Change the leaderboard metric to "FVE Binomial"
Sample Algorithm and Model
Decision Tree Classifier
Click decision tree classifier to access blueprint
Steps to create tree
Split the feature into two groups at the point of the feature where the two groups are as homogenous as possible
Repeat step 2 for each new branch (box)
Find the most predictive feature
ROC Curve
Click on the ROC Curve text
Components
Prediction Distribution
Frequency/Density Distribution
Cross Validation/Validation
Threshold
Confusion Matrix
False Positive Rate (FPR)
Aka Fallout
Matthews Correlation Coefficient (MCC)
Dynamic Measure
Area Under the ROC curve
PPV Positive prediction Value
AKA Precision
Number of cases in the bottom right divided by the number of cases in the right two quadrants
Shows how often the model is correct when indicating something positive
True Positive Rate
Aka Sensitivity
The number of cases in the bottom right quadrant divided by the number of cases in the two bottom quadrants