Model drift controller - Classification

This component is useful to track model performance of a classification model.

The component needs as input the true label column, the prediction made by the model and the estimated probability of the reference class to occur.
Finally, the component controls for predictors' shape and a measure of distrubutional divergence is computed. An high value for a significant number of predictors could cause a model drift, potentially leading to a downgrade of the predictive power.

The following columns must be correctly idetified in the configuration dialog:
-Target varable
-Target prediction
-Probability column
-List of predictors used

Input ports

1. Type: Table
   Test set current mode
   On this table, the reference model performance are computed (Should be the scored test from the traning workflow)
2. Type: Table
   New scored data
   New stream of data already labeled and scored by the model

Output ports

1. Type: Table
   Accuracy metrics
   Global accuracy, sensitivity and specificity
2. Type: Table
   AUC
   Area Under the Curve and percentage change
3. Type: Table
   Distributional divergence
   Measure of the Kullback-Leiber divergence for each predictor