Timely detection of abnormal electricity consumption behaviors plays a key role in saving energy. However, the detection of abnormal electricity consumption faces many problems. Imbalanced data are important challenges in this field. When the normal data are much more than the abnormal data, the network can hardly recognize the features of the minority class data, which generates low detection efficiency. Therefore, in this paper, we employ adaptive synthetic sampling (ADASYN) to achieve effective expansion of the minority class data. In addition, we adopt gated recurrent units to complete the classification of electricity consumption data. We conduct detailed experiments to verify this proposed method. Experimental results show that this method is more effective than other methods.