Customer Churn Prediction in Telco Industry Using Artificial Neural Networks

Dorina Kabakchieva and Hristo Yanchev
Additional contact information
Dorina Kabakchieva: University of National and World Economy, Sofia, Bulgaria
Hristo Yanchev: University of National and World Economy, Sofia, Bulgaria

Innovative Information Technologies for Economy Digitalization (IITED), 2024, issue 1, 323-332

Abstract: Customer churn is a well-known problem in many industries. The cost, in terms of money and time, for acquiring new customers is several times higher than retaining the existing ones. Therefore, developing a process in order to find these customers before they churn is crucial for the business, thus the company resources could be utilized for future projects instead of fulfilling clients shortage. Customer churn prediction is performed by carefully analyzing customer data including number of calls, length of calls, internet services used, tenure, monthly charges, technical support availability, etc. The effect of data normalization in an Artificial Neural Network model, applied to a dataset of 7043 customers in the telecom industry, is analyzed in this paper. Experiments with data normalization in an ANN model for finding potential customer churn, and the selection of training and testing partitions in the modelling phase, are conducted in the presented research. The achieved results reveal that data normalization is a must when using a Neural Network model and higher total accuracy doesn’t mean higher class prediction percentage.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.unwe.bg/doi/iited/2024/IITED.2024.42.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nwe:iitfed:y:2024:i:1:p:323-332

Access Statistics for this article

More articles in Innovative Information Technologies for Economy Digitalization (IITED) from University of National and World Economy, Sofia, Bulgaria Contact information at EDIRC.
Bibliographic data for series maintained by Vanya Lazarova ().