A Proposed Framework for Measuring Customer Satisfaction and Product Recommendation for Ecommerce

Ecommerce is a significant part in the global economy. Ecommerce websites users have high suppositions for the quality of products or services it provides, and if they are not met, the next ecommerce site is only a click away. Managing customer satisfaction, trust and loyalty of ecommerce services is very important for the long-term growth of many businesses. The tremendous growth of consumer-generated content on these sites has led to the development of big data analytics to solve real-life problems. This study aims to examine and demonstrate the utility of big data analytics to understand various important ecommerce-issues, namely the relationship between customer product reviews and satisfaction. Specifically, this study acknowledges semantic analysis and machine learning approach to a large quantity of consumer reviews to deconstruct consumer product reviews and examine its association with satisfaction ratings. This paper studies various approaches to build a framework for an ecommerce which is capable of assessing and modeling satisfaction of customers as well as deducing business intelligence for managers from online product reviews.