Application of Data Mining in Arrear Risks Prediction of Power Customer
Jing-min Wang
Yu-qian Wen
North China Electr. Power Univ., Baoding;
This paper appears in: Knowledge Acquisition and Modeling, 2008. KAM '08. International Symposium on
Publication Date: 21-22 Dec. 2008
On page(s): 206-210
Location: Wuhan,
ISBN: 978-0-7695-3488-6
INSPEC Accession Number: 10453443
Digital Object Identifier: 10.1109/KAM.2008.134
Current Version Published: 2008-12-30
Abstract
Difficulties in collection of electric toll have affected the normal operation and development of power supply bureau seriously. So the arrear problem of power customer has become one of the focus questions that power supply bureau pays attention to. In this paper, based on information entropy theory and on data mining technology, we have proposed a new data mining approach. This approach can measure the information amount of each index which was used to predict the arrear risks of power customer. With this approach, we have got an index system that can reflect the arrear risks. And then, support vector machines (SVM) was used to predict the arrear risks. Through empirical analysis, it has shown that the proposed approach used to arrear risk prediction had higher classification accuracy. So, it is promising to arrear risks prediction of power customer.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
