Introduction to Decision Trees - Data Mining with Decision Trees: Theory and Applications - page 10

map the input space into a real-valued domain. For instance, a regressor can
predict the demand for a certain product given its characteristics. Classifiers
map the input space into predefined classes. For example, classifiers can
be used to classify mortgage consumers as good (full mortgage pay back
on time) and bad (delayed pay back). Among the many alternatives for
representing classifiers, there are for example, support vector machines,
decision trees, probabilistic summaries, algebraic function, etc.
This topic deals mainly with classification problems. Along with
regression and probability estimation, classification is one of the most
studied approaches, possibly one with the greatest practical relevance.
The potential benefits of progress in classification are immense since the
technique has great impact on other areas, both within data mining and in
its applications.
1.7 Classification Trees
While in data mining a decision tree is a predictive model which can
be used to represent both classifiers and regression models, in operations
research decision trees refer to a hierarchical model of decisions and their
consequences. The decision maker employs decision trees to identify the
strategy which will most likely reach its goal.
When a decision tree is used for classification tasks, it is most commonly
referred to as a classification tree. When it is used for regression tasks, it is
called a regression tree.
In this topic, we concentrate mainly on classification trees. Classifica-
tion trees are used to classify an object or an instance (such as insurant)
into a predefined set of classes (such as risky/non-risky) based on their
attributes values (such as age or gender). Classification trees are frequently
used in applied fields such as finance, marketing, engineering and medicine.
The classification tree is useful as an exploratory technique. However, it
does not attempt to replace existing traditional statistical methods and
there are many other techniques that can be used to classify or predict
the aliation of instances with a predefined set of classes, such as artificial
neural networks or support vector machines.
Figure 1.4 presents a typical decision tree classifier. This decision tree is
used to facilitate the underwriting process of mortgage applications of a cer-
tain bank. As part of this process the applicant fills in an application form
that includes the following data: number of dependents (DEPEND), loan-
to-value ratio (LTV), marital status (MARST), payment-to-income ratio