Open AccessUser behaviour analysis and churn prediction in ISP
Author(s) -
Ahmet Turkmen,
Cenk Anıl Bahçevan,
Youssef Alkhanafseh,
Esra Karabıyık
Publication year - 2020
Publication title -
new trends and issues proceedings on advances in pure and applied sciences
Language(s) - English
Resource type - Journals
ISSN - 2547-880X
DOI - 10.18844/gjpaas.v0i12.4987
Subject(s) - computer science , boosting (machine learning) , revenue , customer retention , customer intelligence , gradient boosting , data mining , customer satisfaction , service (business) , machine learning , random forest , service quality , business , finance , marketing
There is no doubt that customer retention is vital for the service sector as companies’ revenue is significantly based on their customers’ financial returns. The prediction of customers who are at the risk of leaving a company’s services is not possible without using their connection details, support tickets and network traffic usage data. This paper demonstrates the importance of data mining and its outcome in the telecommunication area. The data in this paper are collected from different sources like Net Flow logs, call records and DNS query logs. These different types of data are aggregated together to decrease the missing information. Finally, machine learning algorithms are evaluated based on the customer dataset. The results of this study indicate that the gradient boosting algorithm performs better than other machine learning algorithms for this dataset.
Keywords: Data analysis, customer satisfaction, subscriber churn, machine learning, telecommunication.