Fraud Detection in Energy Consumption: A Supervised Approach
Authors:
- Bernat Coma-PuigBCBernat Coma-Puig
- Josep CarmonaJCJosep Carmona
- Ricard GavaldaRGRicard Gavalda
- Santiago AlcoverroSASantiago Alcoverro
- Victor MartinVMVictor Martin
- 26 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 120-129
Abstract
Data from utility meters (gas, electricity, water) is a rich source of information for distribution companies, beyond billing. In this paper we present a supervised technique, which primarily but not only feeds on meter information, to detect meter anomalies and customer fraudulent behavior (meter tampering). Our system detects anomalous meter readings on the basis of models built using machine learning techniques on past data. Unlike most previous work, it can incrementally incorporate the result of field checks to grow the database of fraud and non-fraud patterns, therefore increasing model precision over time and potentially adapting to emerging fraud patterns. The full system has been developed with a company providing electricity and gas and already used to carry out several field checks, with large improvements in fraud detection over the previous checks which used simpler techniques.Keywords
This publication has 11 references indexed in Scilit:
- Nontechnical Losses detection: A Discrete Cosine Transform and Optimum-Path Forest based approach2015
- Fraud detection in registered electricity time seriesInternational Journal of Electrical Power & Energy Systems, 2015
- Improving Knowledge-Based Systems with statistical techniques, text mining, and neural networks for non-technical loss detectionKnowledge-Based Systems, 2014
- Using the rough set theory to detect fraud committed by electricity customersInternational Journal of Electrical Power & Energy Systems, 2014
- A game theory model for electricity theft detection and privacy-aware control in AMI systems2012
- Detection of frauds and other non-technical losses in a power utility using Pearson coefficient, Bayesian networks and decision treesInternational Journal of Electrical Power & Energy Systems, 2012
- Nontechnical Loss Detection for Metered Customers in Power Utility Using Support Vector MachinesIEEE Transactions on Power Delivery, 2009
- Power Utility Nontechnical Loss Analysis With Extreme Learning Machine MethodIEEE Transactions on Power Systems, 2008
- Wavelet based feature extraction and multiple classifiers for electricity fraud detection2003
- Data mining in a power company customer databaseElectric Power Systems Research, 2000