Fraud detection in high voltage electricity consumers using data mining

José E. Cabral; João O.P. Pinto; Evandro M. Martins; Alexandra M.A.C. Pinto

doi:10.1109/TDC.2008.4517232

Fraud detection in high voltage electricity consumers using data mining

José E. Cabral, João O.P. Pinto, Evandro M. Martins, Alexandra M.A.C. Pinto

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

30 Scopus citations

Abstract

This work presents a methodology and a computational system for fraud detection for high voltage electrical energy consumers using data mining. This methodology is based on a non-supervised artificial neural network called SOM (Self-Organizing Maps), which allows the identification of the consumption profile historically registered for a consumer, and its comparison with present behavior, and shows possible frauds. From the automatic consumer behavior pre-analysis, electrical energy companies will better direct its inspections, and will reach higher rates of correctness. The fraud detection system validation showed that the methodology is robust on the cases of lower consumption resulted by fraud, and on the cases of atypicality intrinsic to the consumer.

Original language	English
Title of host publication	Transmission and Distribution Exposition Conference
Subtitle of host publication	2008 IEEE PES Powering Toward the Future, PIMS 2008
DOIs	https://doi.org/10.1109/TDC.2008.4517232
State	Published - 2008
Externally published	Yes
Event	Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008 - Chicago, IL, United States Duration: Apr 21 2008 → Apr 24 2008

Publication series

Name	Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008

Conference

Conference	Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008
Country/Territory	United States
City	Chicago, IL
Period	04/21/08 → 04/24/08

Keywords

Artificial intelligence
Data mining
Fraud detection
KDD
Self-organizing maps

Access to Document

10.1109/TDC.2008.4517232

Cite this

Cabral, J. E., Pinto, J. O. P., Martins, E. M., & Pinto, A. M. A. C. (2008). Fraud detection in high voltage electricity consumers using data mining. In Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008 Article 4517232 (Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008). https://doi.org/10.1109/TDC.2008.4517232

@inproceedings{b586e0fe265742f39e31d208ef568889,

title = "Fraud detection in high voltage electricity consumers using data mining",

abstract = "This work presents a methodology and a computational system for fraud detection for high voltage electrical energy consumers using data mining. This methodology is based on a non-supervised artificial neural network called SOM (Self-Organizing Maps), which allows the identification of the consumption profile historically registered for a consumer, and its comparison with present behavior, and shows possible frauds. From the automatic consumer behavior pre-analysis, electrical energy companies will better direct its inspections, and will reach higher rates of correctness. The fraud detection system validation showed that the methodology is robust on the cases of lower consumption resulted by fraud, and on the cases of atypicality intrinsic to the consumer.",

keywords = "Artificial intelligence, Data mining, Fraud detection, KDD, Self-organizing maps",

author = "Cabral, {Jos{\'e} E.} and Pinto, {Jo{\~a}o O.P.} and Martins, {Evandro M.} and Pinto, {Alexandra M.A.C.}",

year = "2008",

doi = "10.1109/TDC.2008.4517232",

language = "English",

isbn = "9781424419036",

series = "Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008",

booktitle = "Transmission and Distribution Exposition Conference",

note = "Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008 ; Conference date: 21-04-2008 Through 24-04-2008",

}

Cabral, JE, Pinto, JOP, Martins, EM & Pinto, AMAC 2008, Fraud detection in high voltage electricity consumers using data mining. in Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008., 4517232, Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008, Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008, Chicago, IL, United States, 04/21/08. https://doi.org/10.1109/TDC.2008.4517232

Fraud detection in high voltage electricity consumers using data mining. / Cabral, José E.; Pinto, João O.P.; Martins, Evandro M. et al.
Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008. 2008. 4517232 (Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Fraud detection in high voltage electricity consumers using data mining

AU - Cabral, José E.

AU - Pinto, João O.P.

AU - Martins, Evandro M.

AU - Pinto, Alexandra M.A.C.

PY - 2008

Y1 - 2008

N2 - This work presents a methodology and a computational system for fraud detection for high voltage electrical energy consumers using data mining. This methodology is based on a non-supervised artificial neural network called SOM (Self-Organizing Maps), which allows the identification of the consumption profile historically registered for a consumer, and its comparison with present behavior, and shows possible frauds. From the automatic consumer behavior pre-analysis, electrical energy companies will better direct its inspections, and will reach higher rates of correctness. The fraud detection system validation showed that the methodology is robust on the cases of lower consumption resulted by fraud, and on the cases of atypicality intrinsic to the consumer.

AB - This work presents a methodology and a computational system for fraud detection for high voltage electrical energy consumers using data mining. This methodology is based on a non-supervised artificial neural network called SOM (Self-Organizing Maps), which allows the identification of the consumption profile historically registered for a consumer, and its comparison with present behavior, and shows possible frauds. From the automatic consumer behavior pre-analysis, electrical energy companies will better direct its inspections, and will reach higher rates of correctness. The fraud detection system validation showed that the methodology is robust on the cases of lower consumption resulted by fraud, and on the cases of atypicality intrinsic to the consumer.

KW - Artificial intelligence

KW - Data mining

KW - Fraud detection

KW - KDD

KW - Self-organizing maps

UR - http://www.scopus.com/inward/record.url?scp=77950962653&partnerID=8YFLogxK

U2 - 10.1109/TDC.2008.4517232

DO - 10.1109/TDC.2008.4517232

M3 - Conference contribution

AN - SCOPUS:77950962653

SN - 9781424419036

T3 - Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008

BT - Transmission and Distribution Exposition Conference

T2 - Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008

Y2 - 21 April 2008 through 24 April 2008

ER -

Cabral JE, Pinto JOP, Martins EM, Pinto AMAC. Fraud detection in high voltage electricity consumers using data mining. In Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008. 2008. 4517232. (Transmission and Distribution Exposition Conference: 2008 IEEE PES Powering Toward the Future, PIMS 2008). doi: 10.1109/TDC.2008.4517232

Fraud detection in high voltage electricity consumers using data mining

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this