An E-Commerce Recommendation System Based on Dynamic Analysis of Customer Behavior

The expansion of e-commerce site platforms has brought about the need for personalized recommendation systems for the betterment of user experience and sales. In this paper, we propose a new approach for the recommendation system which is based on the dynamic behavior analysis of the users of the system. This involves analytics on the current data about customer activities such as buying history, browsing history, and likes to give recommendations that are up to date and very precise. Static models of the recommendation systems are contrasted to dynamic ones with the emphasis on the benefits of using for example collaborative filtering, content based filtering and other machine learning based hybrid systems to such systems. The performance metrics of accuracy, recall and F1 score confirm that the implementation of the system as proposed solves the cold start problem, enhances the scalability of the system and improves the accuracy of recommendations made. This work therefore opens the door to next generation recommendation engines which are more e-commerce oriented and can respond to the changing needs of customers more effectively.