Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Customer Churn Prediction for Financial Institutions Using Deep Learning Artificial Neural Networks in Zimbabwe

Customer Churn Prediction for Financial Institutions Using Deep Learning Artificial Neural Networks in Zimbabwe
View Sample PDF
Author(s): Panashe Chiurunge (Chinhoyi University of Technology, Zimbabwe), Agripah Kandiero (Instituto Superior Mutasa, Mozambique & Africa University, Zimbabwe)and Sabelo Chizwina (North-West University, South Africa)
Copyright: 2024
Pages: 39
Source title: Theoretical and Conceptual Frameworks in ICT Research
Source Author(s)/Editor(s): Agripah Kandiero (Insituto Superior Mutasa (ISMU), Mozambique & Mozambique Institute of Technology, Mozambique & Africa University, Zimbabwe), Stanislas Bigirimana (Africa University, Zimbabwe)and Sabelo Chizwina (University of South Africa, South Africa)
DOI: 10.4018/978-1-7998-9687-6.ch010



The research was conducted to develop a customer churn predictive modelling using deep neural networks for financial institutions in Zimbabwe using a local leading financial institution. This was based on a need to perform a customer churn analysis and develop a very high accurate and reliable customer churn predictive model. In this era, every customer counts, hence once acquired a business should do everything in its power to keep that customer because the cost of acquiring a new customer is far greater than the cost of keeping an existing one. Therefore the need to ascertain customers who have churned and also be at a position to anticipate those who are churning or are about to churn then take corrective measures to keep such customers on board. The study followed one of the data science research methodologies called CRoss industry standard process for data mining (CRISP-DM) which involves understanding the business, understanding the data, data preparation, modelling, validating the model then deployment of the model.

Related Content

Elisha Mupaikwa, Kelvin Joseph Bwalya. © 2024. 28 pages.
Nkholedzeni Sidney Netshakhuma. © 2024. 21 pages.
Amrita Sarkar, Satyaki Sarkar. © 2024. 27 pages.
Ahmad Said, Yulita Hanum P. Iskandar. © 2024. 17 pages.
Manish Kumar. © 2024. 19 pages.
Stansilas Bigirimana, Ganyanhewe Masanga. © 2024. 22 pages.
Mampilo M. Phahlane. © 2024. 20 pages.
Body Bottom