Classification with Decision Trees. Instructor: Qiang Yang Hong Kong University of Science and Technology [email protected] Thanks: Eibe Frank and Jiawei Han. DECISION TREE [Quinlan93]. An internal node represents a test on an attribute.
Note: this is
Splitting stops when data can’t be split any further
where pj is the relative frequency of class j in T. gini(T) is minimized if the classes in T are skewed.
25% confidence interval
If we have a
single leaf node
If we split, we can
this gives 0.51