Universiti Teknologi Malaysia Institutional Repository

Predicting churn: how MultiLayer Perceptron method can help with customer retention in telecom industry

Sjarif, Nilam Nur Amir and Azmi, N. F. and Sarkan, H. M. and Sam, S. M. and Osman, M. Z. (2020) Predicting churn: how MultiLayer Perceptron method can help with customer retention in telecom industry. In: 2nd Joint Conference on Green Engineering Technology and Applied Computing 2020, IConGETech 2020 and International Conference on Applied Computing 2020, ICAC 2020, 4 February 2020 - 5 February 2020, Bangkok, Thailand.


Official URL: http://dx.doi.org/10.1088/1757-899X/864/1/012076


Customer churn prediction has been used widely in various kind of domain especially subscription-basis industries. With the rapid growth of telecommunication industry over the last decade, this industry not only focuses on providing numerous products, but also satisfying the customers as it is one of the key solutions to remain competitive. This research proposed MultiLayer Perceptron Method for churn prediction. The evaluation is compared with three classifiers which includes are Support Vector Machine, Naïve Bayes and Decision Tree in term of several aspects. In preprocessing phase, we employed Principal Component Analysis and normalization to find the correlation among all the variables. For the postprocessing, InfoGainAttribute is used to identify the highest factor attribute that leads to customer retention. It is found that MultiLayer Perceptron outperforms other classifiers and international plan plays important role to retain customer from leaving organization.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:MultiLayer Perceptron, churn, customer retention
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > T Technology (General) > T58.5-58.64 Information technology
Divisions:Razak School of Engineering and Advanced Technology
ID Code:92394
Deposited By: Yanti Mohd Shah
Deposited On:28 Sep 2021 15:44
Last Modified:28 Sep 2021 15:44

Repository Staff Only: item control page