Early Prediction of Customer Abandonment in E-Business

Abstract

Customer churn, customer retention and attrition are topics which have been discussed and studied in so many researches. However, most of them have evaluated the churn prediction only based on the history data. Here in this research conduct, it is intended to derive results based on the customer segmentation. Considering the whole customer base might deliver the desirable output yet, when applying the customer segmentation based on the primary customer types, the final outcome will be more precise. Considering the customer type such as, loyalty and seasonal customers who really gives a better return on investment for the business conduced more customer churn and retention evaluation. By referring the E-Business dataset specifically with the access mode and channels of the customers, the tendency of leaving the system with the possible way is to be evaluated. Getting into the term ‘Churn’, this study has aware of the nature of the detachment considering the access channel or method of the customer as well. The suggested methodology would be approaching in two different paths in order to evaluate the best fit and the performance by measuring the accuracy and the reusability of the model. Aligning with two methods namely logistic regression and deep neural network address artificial neural network, the predictive model would be implemented. Specifically with the use of RFM Analysis, the study will be directed to customer segmentation. The segmentation would be involved in clustering for the customer segmentation and as for the predictive model, classification model would be used with class variable for identification of the user churn. Here in this study, main focus would be designing and building predictive models in different aspects under the similar criteria and mostly the evaluating the usefulness of segmentation of the customer over the total customer base that has been dedicated under specific clusters identified with the given set of criteria.