Decision tree learning builds a classification tree, where each node corresponds to one of the attributes; edges correspond to a possible value (or intervals) of the attribute from which the node originates; and each leaf corresponds to a class label. A decision tree can be used to visually and explicitly represent the prediction model, which makes it a very transparent (white box) classifier. Notable algorithms are ID3 and C4.5, although many alternative implementations and improvements exist (for example, J48 in Weka).