Simple Data Augmentation Tricks for Boosting Performance on Electricity Theft Detection Tasks

In practical engineering, electricity theft detection is usually performed on highly imbalanced datasets (i.e., the number of fraudulent samples is much smaller than the benign ones), which limits the accuracy of the classifier. To alleviate the data imbalance problem, this article proposes simple data augmentation tricks (SDAT) to boost performance on electricity theft detection tasks. SDAT includes five simple but powerful operations: adding noises to electricity consumption readings, drifting values of electricity consumption readings, quantizing electricity consumption readings to a level set, adding a fixed value to electricity consumption readings, and adding changeable values to electricity consumption readings. In addition, eight potential tricks are also mentioned. Numerical simulations are conducted on a real-world dataset. The simulation results show that SDAT can significantly boost the performance of different classifiers, especially for small datasets. Besides, specific suggestions on how to select parameters of SDAT are provided for its migration use to other datasets.

Automated summary

In this article, simple data augmentation tricks (SDAT) are proposed to address the data imbalance issue in electricity theft detection. Five simple but powerful operations are introduced, including adding noises, drifting values, quantizing readings, adding fixed and changeable values. Numerical simulations on a real-world dataset demonstrate that SDAT can significantly improve the performance of different classifiers, particularly for small datasets. Specific suggestions on parameter selection for SDAT's transferability to other datasets are also provided.