The same source also lists several fraud detection applications including: intrusion detection, fraud detection, fault/damage detection, medical and public health anomaly detection, industrial damage detection, image processing, anomaly detection in text data, sensor networks and other domains. Here are a few papers that deal specifically with detection of electricity fraud.
In [2], detection of fraud and other non-technical losses in distribution companies is based on the use of Pearson’s coefficient, Bayesian networks and decision trees. The key idea of these methods is identification of a customer pattern with a drastic drop in consumption and subsequent stabilization, but a gradual (significant) drop with subsequent stabilization of further consumption is also taken into consideration.
In [3], MIDAS is the name of the project which has developed two methodologies for fraud detection (the dominant part of nontechnical losses). One is based on neural networks and the other on statistical techniques. The first methodology uses neural networks due to problem conditions and works with the Kohonen network structure. The second methodology is based on the detection of tolerant values outside the range (outliers).