Deep Learning for Customer Churn Prediction in E-Commerce Decision Support

Churn prediction is a Big Data domain, one of the most demanding use cases recent time. It also critical indicators healthy and growing business, irrespective size or channel sales. This paper aims to develop deep learning model for customers’ churn in e-commerce, which main contribution article. The experiment was performed over real e-commerce data where 75% buyers are one-off customers. based on this business specificity (many customers very few regular ones) extremely challenging and, natural way, must be inaccurate certain ex-tent. Looking from another perspective, correct subsequent actions resulting higher customer retention attractive overall performance. In such case, predictions with 74% accuracy, 78% precision, 68% recall promising. Also, fills research gap contrib-utes existing literature area developing method retail sector by using tools full history each customer’s transactions.