michaelmelese/Customer-Segmentation

This work shows the customer segmentation of the Commercial Bank of Ethiopia is # Customer Segmentation This work shows the customer segmentation of the Commercial Bank of Ethiopia and the paper is published in IEEE. # Abstract Identification of churned customers is critical to the operation and growth of any business. Identification of churned customers can assist businesses in understanding the reasons for churn and planning market strategies to boost business growth. The purpose of this study is to design and develop a machine learning model that can accurately predict churned customers from the total customers of the Commercial Bank of Ethiopia (CBE) in order to retain existing customers. A total of 204,161 datasets with eleven attributes were used for this study. For this study, the overall accuracy of the model was used as the evaluation metric to determine the best classifier. Accordingly, supervised machine learning methods such as Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbor, and Deep Neural Network were used to predict customer churn in a Commercial Bank of Ethiopia (CBE) context. Based on previous literature, these classifier algorithms for customer churn prediction have been widely used. In this study, feature importance and a correlation matrix were used to select features. Furthermore, the SMOTE technique is used to balance the data, and the results for the chosen algorithm were evaluated and compared. Among the various experiments performed, a Deep Neural Network (DNN) outperformed with an accuracy of 79.32%, precision of 85.08%, and recall of 78.19%. # Article available @ ieeexplore.ieee.org If you are using this data please cite the following paper. @inproceedings{seid2022customer, title={Customer Churn Prediction Using Machine Learning: Commercial Bank of Ethiopia}, author={Seid, Muhamed Hassen and Woldeyohannis, Michael Melese}, booktitle={2022 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)}, pages …