الفهرس 
صفحة العنوانOnly 14 pages are availabe for public view
 |  | from | 189 |  |  |
| | | from | 189 | | |
Abstract
Research Objectives:
Many authors have presented different versions of techniques used for improving customer retention greatly based on traditional machine learning techniques. The aim of our research is to apply the most important techniques to improve customer retention developed over the recent years known as deep learning techniques. In our research, we will improve dataset quality by using some data preprocessing techniques, such as error correction, resolving data inconsistency, noise removal, filling null values, feature selection, feature scaling (normalization), and discretization have been applied to the dataset.
Abstract
Customer retention is the most essential challenge going through the companies. Acquiring a new customer is a costly process, so organizations should try to keep their existing loyal customers to increase their profit, revenue and avoid customer churn. The deep learning techniques have a significant impact on improving and predicting customer retention. There are a lot of scientific papers that use machine learning techniques to improve customer retention, but these techniques face a lot of challenges in terms of accuracy. For this purpose, the research community began to use deep learning techniques to improve customer retention and these techniques increase the accuracy, but they did not focus on improving dataset quality. Therefore, the main aim of this research is to introduce a framework that can be used to improve customer retention in telecommunications companies by using deep learning techniques. in addition, this research focused on improving dataset quality using data pre-processing techniques, such as fill null values, feature scaling (normalization, standardization), discretization, and dimensionality reduction to maximize the accuracy. The experiment is performed on a telecom dataset obtained from Kaggle called Cell2Cell. The result of our research paper achieved more accurate results especially in predicting the loss of customers and improving customer retention by applying data quality techniques with Deep Neural Network (DNN) and Artificial Neural Network (ANN). Our proposed model achieved good performance in terms of accuracy and the results demonstrated that the predictive DNN model for improving customer retention achieved 99.80% of accuracy and 98.94% by using ANN.