Loading...
Loading...

Go to the content (press return)

Fraud detection in energy consumption: a supervised approach

Author
Coma, B.; Carmona, J.; Gavaldà, R.; Alcoverro, S.; Martín, V.
Type of activity
Presentation of work at congresses
Name of edition
3rd IEEE International Conference on Data Science and Advanced Analytics
Date of publication
2016
Presentation's date
2016-10-17
Book of congress proceedings
3rd IEEE International Conference on Data Science and Advanced Analytics, DSAA 2016: 17-19 October 2016, Montreal, PQ, Canada: proceedings
First page
120
Last page
129
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
DOI
https://doi.org/10.1109/DSAA.2016.19 Open in new window
Repository
http://hdl.handle.net/2117/101913 Open in new window
URL
http://ieeexplore.ieee.org/document/7796897/?reload=true&part=1 Open in new window
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 resu...
Citation
Coma-Puig, B., Carmona, J., Gavaldà, R., Alcoverro, S., Martín, V. Fraud detection in energy consumption: a supervised approach. A: IEEE International Conference on Data Science and Advanced Analytics. "3rd IEEE International Conference on Data Science and Advanced Analytics, DSAA 2016: 17-19 October 2016, Montreal, PQ, Canada: proceedings". Montréal: Institute of Electrical and Electronics Engineers (IEEE), 2016, p. 120-129.
Keywords
Data analysis, Fraud, Learning (artificial intelligence), Public utilities
Group of research
ALBCOM - Algorithms, Computational Biology, Complexity and Formal Methods
LARCA - Laboratory of Relational Algorithmics, Complexity and Learnability

Participants

Attachments