A Data-Distribution-Based Imbalanced Data Classification Method for Credit Scoring Using Neural Networks

Credit scoring is always a hot topic for the researchers because of its profitability. In this paper, we proposed a novel data-distribution based imbalanced data classification method to construct the credit scoring model using BP neural networks. The method distinguished itself by focusing on the distribution of the data and artificially changes the probabilities of the sampling for the purpose of centralizing the edge samples. The German Credit Dataset is applied for verifying the effectiveness of the method, and the experiment results show that the classifiers constructed by the proposed method performs better for the imbalanced credit data classification.