Aiming at the problems of sample imbalance and category overlap in personal credit risk assessment,an improved active generative oversampling model is proposed.Firstly,based on the auxiliary classifier generative adversarial network(ACGAN)framework,Wasserstein distance is introduced to improve the true false discrimination loss function,and gradient penalty is added to prevent pattern collapse;Second-ly,Focal loss is used instead of traditional cross entropy loss to enhance the ability to identify difficult samples;Finally,the proposed model is used to oversample imbalanced data to improve classifier performance.Experiments on real credit data show that the model improves the classifier's classification performance indicators F1,AUC,and G-means by 11.2%,1.7%,and 12.8%,respectively.It achieves significant results in enhancing sample diversity,reducing class overlap,and improving the classifier's classification performance on imbalanced datas-ets.
关键词
深度学习/不平衡数据/类重叠/ACGAN/focal/loss/Wasserstein距离
Key words
deep learning/unbalanced data/class overlap/ACGAN/focal loss/Wasserstein distance
维普
万方数据