Of course, researchers have experimented with many other attribute selection methods that you might come across. Here are some of the most well-known that you might like to look into further.
- CHAID: a popular decision tree algorithm, measure based on χ2 test for independence
- C-SEP: performs better than info. gain and gini index in certain cases
- G-statistic: has a close approximation to χ2 distribution
- MDL (Minimal Description Length) principle(i.e., the simplest solution is preferred):
- The best tree as the one that requires the fewest number of bits to both (1) encode the tree, and (2) encode the exceptions to the tree
- Multivariate splits (partition based on multiple variable combinations), e.g. CART: finds multivariate splits based on a linear combination of attributes.
若有收获，就点个赞吧
0 人点赞
