International Journal of Computer Engineering & Applications
The multirelational classification algorithms are designed to search for patterns across multiple interlinked relations in a relational database. For better classification these methods search for relevant features from a target relation and the relations related to it. Most of these methods are based on the assumption that the classes in the target relation are equally represented. They thus tend to produce poor predictive performance over the underrepresented class in the data. In case of imbalance database the problem of learning from imbalanced data is a relatively new challenge that has attracted growing attention from both academia and industry.