A neural network approach to discover attribute dependency for improving the performance of classification

The decision tree learning algorithms, e.g., C5, are good at dataset classification. But those algorithms usually work with only one attribute at a time and adopt the greedy method to build the decision tree. The dependencies among attributes are not considered in those algorithms. Unfortunately, in the real world, most datasets contain attributes, which are dependent. Thus, the results generated by those algorithms are not the optimal learning results. However, it is a combinatorial explosion problem for considering multiple attributes at a time. So, it is very important to construct a model to efficiently discovery the dependencies among attributes, and to improve the accuracy and effectiveness of the decision tree learning algorithms. Generally, these dependencies are classified into two types: categorical-type and numerical-type dependencies. This paper proposes a Neural Decision Tree (NDT) model, to deal with these two kinds of dependencies. The NDT model combines the neural network technologies and the traditional decision-tree learning capabilities, to handle the complicated and real cases. According to the experiments on ten datasets from the UCI database repository, the NDT model can significantly improve the accuracy and effectiveness of C5.