Decision Tree (page 5 of 5)

Advantages of Decision Tree: 1) May be used for regression or classification, 2) May be displayed graphically, 3) Highly interpretable, 4) Prediction is fast, 5) Features don’t need scaling, 6) Ignores irrelevant features, 7) Non-parametric, & 8) Follows the same approach as humans generally follow for decision making.

Disadvantages of Decision Tree: 1) Not good in performance when compared to other Supervised Machine Learning Algorithm, 2) Due to overfitting we do Tuning, 3) Due to the presence of highly unbalanced classes, it may not work well, & 4) Doesn’t work well when the dataset is very small.

Reading Check: “The highest compliment that you can pay me is to say that I work hard every day, that I never dog it.” – Wayne Gretzky

Inclass Scenario: Predicting Customer Types using the Decision Tree Algorithm