In the machine learning community, a decision tree is a branching set of rules used to classify a record, or predict a continuous value for a record. For example, one path in a tree modeling customer churn (abandonment of subscription) might look like this:
IF payment is month-to-month, IF customer has subscribed less than 6 months, IF customer uses a Mac, THEN “churn” is the prediction.
The rules in such a tree are derived by machine learning methods such as CART.
In the operations research (OR) community, a decision tree is a branching set of decisions, possible outcomes, and payoffs. The tree is not derived by any automated process but rather is drawn by an analyst, who attaches estimated probabilities to the outcomes of the decisions.