A new oversampling method and improved radial basis function classifier for customer consumption behavior prediction

•A new oversampling method is proposed to solve class imbalance in the real dataset.•A new classifier is proposed to improve the accuracy of consumer behavior prediction.•The hybrid kernel of the radial basis function neural network is designed.•The centers of the neural network are optimized by the immune algorithm.•All results show that the proposed two methods outperform existing models.