The ID3 algorithm is a classical learning algorithm of decision tree in data mining. The algorithm trends to choosing the attribute with more values, affect the efficiency of classification and prediction for building a decision tree. This article proposes a new approach based on an improved ID3 algorithm. The new algorithm introduces the importance factor A when calculating the information entropy. It can strengthen the label of important attributes of a tree and reduce the label of non-important attributes. The algorithm overcomes the flaw of the traditional ID3 algorithm which tends to choose the attributes with more values, and also improves the efficiency and flexibility in the process of generating decision trees.