Evaluation and review of intelligent management system for allocating telecommunications system facilities to predict customer churn based on machine learning and evolutionary algorithms

Evaluation and review of intelligent management system for allocating telecommunications system facilities to predict customer churn based on machine learning and evolutionary algorithms

Maedeh Rahmani1 Farshid Vazifehdoost2 Mehdi Razapoor Mirsaleh3

1) Master s student in Computer Engineering, Software Orientation, Payam Noor University, Kish International Center Email :
2) Graduated with a Master s degree in Computer Engineering, Artificial Intelligence and Robotics, from Payam Noor University, Qeshm International Center Email
3) Assistant Professor, Department of Computer Engineering and Information Technology, Payam Noor University Email :

IOI Code : XKHC-AZKFKB
Publication : 9th.International Conference on Researches in Science & Engineering & 6th.International Congress on Civil, Architecture and Urbanism in Asia(9icrsie.com)
Abstract :
    The ability to predict customer churn can help many companies that are mainly focused on telecommunications to increase revenue and reduce losses. It will also be a large part of strategic decisions and business plan creation and process management. To prevent valuable customers from leaving the service, the extracted data can be used to provide the root cause. In this research, an intelligent management system for allocating telecommunications system resources to predict customer churn based on artificial neural networks (classification of suitable features to detect and predict telecommunications customer churn using artificial neural networks) and the evolutionary algorithm of intelligent droplets are presented (feature selection to reduce the dimension of features and reach the appropriate dataset for attack detection is done based on the evolutionary algorithm of intelligent droplets). Using machine learning techniques, a more accurate model can be obtained. It is not possible to completely eliminate churn, but it is possible to prevent a large percentage of customers from churning. A good model not only provides statistical accuracy, but also provides more insights to create a good telecommunications service with a loyal customer base.

Keywords : management system intelligent facility allocation telecommunications system customer churn prediction machine learning and evolutionary algorithm