Detecção de Fraudes em Unidades Consumidoras de Energia Elétrica Usando Rough Sets
AUTOR(ES)
José Edison Cabral Junior
DATA DE PUBLICAÇÃO
2005
RESUMO
Frauds represent a high percentage of the total commercial losses for electrical energy companies. In general, due to the high number of consumers, in-site inspections are made without any criteria, which cause a low rightness rate. On the other hand, electrical energy companies have information about their consumers stored in their databases. This information could be used to identify behavior patterns that are common among consumers that commit frauds, and this could guide the selection of the consumer that should undergo inspection. This work proposes a KDD and Rough Sets based methodology for consumer fraud detection for electrical energy companies. This methodology helps to find out consumer fraud behavior profiles at the company databases. From these patterns, a set of classification rules are created to fetch consumers that should be inspected. Using such strategy, the companies expect to increase the rightness rate and therefore decrease profit losses due to consumer fraud.
ASSUNTO(S)
energia elétrica - distribuição - medidas de segurança engenharia eletrica rough sets energia elétrica
Documentos Relacionados
- Método para identificação de quedas de consumo atípicas em unidades consumidoras de energia elétrica
- Automação da detecção de fraudes em sistemas de medição de energia elétrica utilizando lógica fuzzy em ambiente SCADA
- Detection of fraud or measurement error in big electric power s consumers using Rough Sets based in historical data and in data based in real time
- DATA MINING WITH ROUGH SETS TECHNIQUES
- MODELAGEM DA MATRIZ ENERGÉTICA DE UNIDADES CONSUMIDORAS CONECTADAS A CONCESSIONÁRIAS DE DISTRIBUIÇÃO DE ENERGIA ELÉTRICA PARA AVALIAÇÃO DA VIABILIDADE TÉCNICO-ECONÔMICA DESSES CONSUMIDORES ADOTAREM COGERAÇÃO A GÁS NATURAL