NAS-FD: Neural Architecture Search-Based Fraud Detection for Power Audit Data

Power data auditing is the cornerstone of a reliable and efficient modern power system. Various deep learning models have been successfully applied to fraud detection in power audit data. However, most of these methods rely on manual trial-and-error and expert knowledge to design the neural architectures and hyper-parameters. To address this limitation, this paper proposes an innovative automated deep learning approach for fraud detection model design using genetic algorithm (GA)-based neural architecture search (NAS), termed NAS-FD. In NAS-FD, convolutional neural network (CNN) is employed as the primary detection model, leveraging its strong data learning and feature extraction capabilities. First, an effective encoding scheme is developed to represent the nueral architectures and hyper-parameters of CNN, as these parameters significantly influence the detection performance. Then, considering detection performance as the objective function, well-designed GA-based evolutionary operations are implemented to optimize the neural architectures and hyper-parameters of CNN, obtaining the optimized CNN. The detection performance of the proposed NAS-FD method is validated using an electricity theft dataset from the power auditing domain. Experimental results demonstrate that NAS-FD achieves superior detection performance compared with manually designed deep learning models in terms of four performance indices including accuracy, precision, recall, and F1-score.