Numerous articles have been written about the use of decision trees to create predictive models. The literature has been rich in detail about the varying techniques and methodologies used to create decision trees. Different approaches in terms of the mathematics being used range from using Chi-Square type statistics to the more engineering-based mathematics such as the use of entropy based algorothms. Virtually all data mining software includes some decision tree type tools. From a theoretical perspective, the more granular multivariate logistic/multiple regression techniques should outperform decision-trees since the output of the multivariate techniques is a score for each
This content is restricted to site members. If you are an existing user, please log in on the right (desktop) or below (mobile). If not, register today and gain free access to original content and industry news. See the details here.