Affiliation:
1. SAKARYA UNIVERSITY
2. BOZOK UNIVERSITY
3. İZMİR BAKIRÇAY ÜNİVERSİTESİ
4. IZMIR BAKIRCAY UNIVERSITY
Abstract
Churn studies have been used for many years to increase profitability as well as to make customer-company relations sustainable. Ordinary artificial neural network (ANN) and convolution neural network (CNN) are widely used in churn analysis due to their ability to process large amounts of customer data. In this study, an ANN and a CNN model are proposed to predict whether customers in the retail industry will churn in the future. The models we propose were compared with many machine learning methods that are frequently used in churn prediction studies. The results of the models were compared via accuracy classification tools, which are precision, recall, and AUC. The results showed that the CNN model produced a 97.62% of accuracy rate which resulted in a better classification and prediction success than other compared models
Publisher
Gazi University Journal of Science
Subject
Multidisciplinary,General Engineering
Reference26 articles.
1. [1] Germann, F., Lilien, G., Moorman, C., Fiedler, L., “Driving customer analytics from the top. Customer Needs and Solutions”, Customer Needs and Solutions, 7(3):43–61, (2021).
2. [2] Germann F, Lilien GL, Fiedler L, Kraus M., “Do retailers benefit from deploying customer analytics?”, Journal of Retailing, 90(4):587-593, (2014).
3. [3] Mishra, A., Reddy, U.S., “A novel approach for churn prediction using deep learning”, Proceedings of the IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), pages 1–4. IEEE, (2017).
4. [4] Aspect Software. Aspect Consumer Index 2020. https://www.aspect.com/the-aspect-consumer-experience-index-2020, 2020. Online, accessed 10April 2021.
5. [5] Uzair Ahmed, Asifullah Khan, Saddam Hussain Khan, Abdul Basit, Irfan Ul Haq, and Yeon Soo Lee. Transfer learning and meta classification based deep churn prediction system for telecom industry. arXiv preprint arXiv:1901.06091, 2019.
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Evrişimsel Sinir Ağları Tabanlı Derin Öğrenme Yöntemiyle Müşteri Şikayetlerinin Sınıflandırılması;Bingöl Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi;2024-06-27
2. Modeling Longitudinal Evolution of Decommissioned Geostationary Satellites using Neural Networks;Fırat Üniversitesi Mühendislik Bilimleri Dergisi;2024-03-28
3. Identifying Customer Churn Patterns Using Machine Learning Predictive Analysis;2023 3rd International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON);2023-12-29
4. Customer Churn Prediction in Telecommunication Industry using Machine Learning and Deep Learning Approach;2023 3rd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA);2023-12-21
5. The Comparison of Random Forest and Artificial Neural Network for Customer Churn Prediction in Telecommunication;2023 3rd International Conference on Smart Cities, Automation & Intelligent Computing Systems (ICON-SONICS);2023-12-06