Classification

Classification

Suppose we label players who spend 5$ or more as HighRollers, and the rest as PennyPinchers.
Our Goal is to build a Decision Tree to predict if an unknown user would be a HighRoller or a PennyPincher.
Then study the built Decision Tree to see what factors predict if a User will drive Revenues.

Steps:

1. Data Preparation:
   Binning avg_price into 2 categories and selecting attributes for Classification.

2. Modelling Decision Tree:
   Splitting our Dataset into Test and Train Dataset.
   And building the decision tree.

3. Evaluation:
   Evaluate the accuracy and Confusion Matrix of the Tree.

4. Conclusion:
   Takes a broader look at the workflow and provides Recommendations to increase Revenue.