Non Technical Loses Detection - Experts Labels vs. Inspection Labels in the Learning Stage

Fernanda Rodríguez, Federico Lecumberry, Alicia Fernández

2014

Abstract

Non-technical losses detection is a complex task, with high economic impact. The diversity and big number of consumption records, makes it very important to find an efficient automatic method for detection the largest number of frauds with the least amount of experts’ hours involved in preprocessing and inspections. This article analyzes the performance of a strategy based on learning from expert labeling: suspect/no-suspect, with one using inspection labels: fraud/no-fraud. Results show that the proposed framework, suitable for imbalance problems, improves performance in terms of the Fmeasure with inspection labels, avoiding hours of experts labeling.

Paper Citation

in Harvard Style

Rodríguez F., Lecumberry F. and Fernández A. (2014). Non Technical Loses Detection - Experts Labels vs. Inspection Labels in the Learning Stage . In Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-018-5, pages 624-628. DOI: 10.5220/0004823506240628

in Bibtex Style

@conference{icpram14,
author={Fernanda Rodríguez and Federico Lecumberry and Alicia Fernández},
title={Non Technical Loses Detection - Experts Labels vs. Inspection Labels in the Learning Stage},
booktitle={Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2014},
pages={624-628},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004823506240628},
isbn={978-989-758-018-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Non Technical Loses Detection - Experts Labels vs. Inspection Labels in the Learning Stage
SN - 978-989-758-018-5
AU - Rodríguez F.
AU - Lecumberry F.
AU - Fernández A.
PY - 2014
SP - 624
EP - 628
DO - 10.5220/0004823506240628