: For over 40 years, researchers manually designed decision-tree algorithms like C4.5 and CART by choosing specific components (splitting criteria, stopping rules, etc.) based on trial and error.

: Automatic Design of Decision-Tree Algorithms with Evolutionary Algorithms

: Rodrigo C. Barros, Márcio P. Basgalupp, André C.P.L.F. de Carvalho, and Alex A. Freitas

: For a more comprehensive look, the authors published a detailed study in the SpringerBriefs in Computer Science series .

: For those new to the concept, the article "A Practical Tutorial for Decision Tree Induction" provides a foundational overview of the evaluation measures used in these algorithms.

: Experimental results across 20 public datasets showed that HEAD-DT could generate algorithms that are significantly more accurate than established human-designed standards like C4.5 and CART.

: Evolutionary Computation (MIT Press), Volume 21, Issue 4, November 2013 Summary of Research