About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Publication
ISGT-Asia 2016
Conference paper
The electricity bill charge risk analysis in power supply company based on a novel predicting method
Abstract
Risk Analysis of electricity bill charge has been both challenging and important in the field of electricity power supply in China. In this paper, a novel electricity bill charge risk predicting method is proposed. The SMOTE (synthetic minority oversampling technique) algorithm is first used to under-sampling the majority class and over-sampling the minority class, and then it is combined with some state-of-the-art classification methods to predict the electricity charge risk based on an imbalanced data set obtained from a power supply enterprise. The results of the empirical analysis demonstrate that a combination of SMOTE algorithm with Random Forest method achieves better classification performance under several criterions. Furthermore, five important variables are listed for power supply enterprises to take corresponding measures to avoid charge risk.