Global Evaluation for Decision Tree Learning
This is an incremental improvement for machine learning practitioners working with decision trees.
The authors tackled the problem of decision tree learning by extending the ID3 algorithm to use global distance metrics from clusterings instead of local leaf evaluations, resulting in a modified approach that shows both strengths and problems compared to the original.
We transfer distances on clusterings to the building process of decision trees, and as a consequence extend the classical ID3 algorithm to perform modifications based on the global distance of the tree to the ground truth--instead of considering single leaves. Next, we evaluate this idea in comparison with the original version and discuss occurring problems, but also strengths of the global approach. On this basis, we finish by identifying other scenarios where global evaluations are worthwhile.