Talk:Optimal discriminant analysis and classification tree analysis

The title and thesis of this Wikipedia article relies on a single published article and is outside the mainstream of statistics and machine learning.

There are a variety of classification techniques developed researchers in a variety of fields and there is a lively competition.

At the moment leading classification techniques based upon their success in competitions such as KDD, Kaggle or Netflix would be random forests or boosting (gradient boosting or gbm). ODA is nowhere to be seen.

See for example Statistical_classification

Moreover, in Decision Tree Learning it is stated: "The problem of learning an optimal decision tree is known to be NP-complete under several aspects of optimality and even for simple concepts[12][13]" Jim.Callahan,Orlando (talk) 17:16, 16 December 2015 (UTC)