Cost-sensitive hierarchical classification for imbalance classes

Abstract

The hierarchical classification with an imbalance class problem is a challenge for in machine learning, and is caused by data with an uneven distribution. Learning from an imbalanced dataset can lead to performance degradation of the classifier. Cost-sensitive learning is a useful solution for handling the gap probability of majority and minority classes. This paper proposes a cost-sensitive hierarchical classification for imbalance classes (CSHCIC), constructing a cost-sensitive factor to balance the relationship between majority and minority classes. First, we divide a large hierarchical classification task into several small subclassification tasks by class hierarchy. Second, we establish a cost-sensitive factor by more precisely using the number of different samples of subclassifications. Then, we calculate the probability of every node using logistic regression. Lastly, we update the cost-sensitive factor using the flexibility factor and the number of samples. The experimental results show that the cost-sensitive hierarchical classification method achieves excellent performance on handling imbalance class datasets. The running time cost of the proposed method is smaller than most state-of-the-art methods.