Home // DBKDA 2017, The Ninth International Conference on Advances in Databases, Knowledge, and Data Applications // View article

Customer Churn Prediction in Telecommunication with Rotation Forest Method

Authors:
Mümin Yıldız
Songül Albayrak

Keywords: Customer Churn Prediction, Data Mining, Telecommunication, Rotation Forest, Antminer.

Abstract:
The main task of customer churn prediction is to estimate subscribers who may want to leave from a company and provide solutions to prevent possible churnes. In recent years, estimating churners before they leave has became valuable in the environment of increased competition among companies. The research in this paper was done to estimate churners for companies in the telecommunication industry showing how prediction efficacy is increased by balancing the data with down sampling and classifying by the rotation forest method.The performance level of these techniques are compared with Antminer and C4.5 decision tree. The comparisons are done by using the dataset taken from American Telecommunication Company and accuracy, sensitivity and specificity are used for the performance criteria.

Pages: 26 to 29

Copyright: Copyright (c) IARIA, 2017

Publication date: May 21, 2017

Published in: conference

ISSN: 2308-4332

ISBN: 978-1-61208-558-6

Location: Barcelona, Spain

Dates: from May 21, 2017 to May 25, 2017