Discriminant Analysis

Sanjiv R. Das

Credit Card Dataset

This dataset is highly imbalanced. We applied an oversampling algorithm (SMOTE) to it and balanced the minority class to be equal in size to the majority class. We saved this in a pickle file and read it in here.

Linear Discriminant Analysis

Discriminant Function

$$ D = a_1 x_1 + a_2 x_2 + ... + a_K x_K = \sum_{k=1}^K a_k x_k $$

$D$ is often replace by $Z$, which leads to the notion of "Z-score" or discriminant score.

Notes: http://srdas.github.io/MLBook/DiscriminantFactorAnalysis.html#discriminant-analysis

NCAA Dataset