Towards real-time customer satisfaction prediction model for mobile internet networks

• Main Authors: Yusuf-Asaju, Ayisat W., Dahalin, Zulkhairi, Ta'a, Azman
• Other Authors: Saeed, Faisal
• Format: Book Section
• Published: Springer, Cham 2018
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://repo.uum.edu.my/25964/; http://doi.org/10.1007/978-3-319-99007-1_10

Satisfying the customers’ service requirements and expectation, especially customer satisfaction had been one of the major challenges faced by the mobile network operators in most telecommunication organizations. This article implemented an analytical customer satisfaction prediction model by employing the mobile internet traffic datasets collected in real-time through the drive test measurement. To this end, the implementation phase has employed machine learning algorithms in the Microsoft Machine Learning R client Server. The results show that previous user’s traffic datasets can be used to predict customer satisfaction and identify the root cause of poor customer experience before the complete deterioration of the service performance, which could lead to larger percentage of customer dissatisfaction. The mobile network operators can also use the proposed model to overcome the drawbacks of the conventional subjective method of analysing customer satisfaction.