Customer Segmentation Using Machine Learning

-------------------------------------------------------------------------***------------------------------------------------------------------------ Abstract - In carrying out successful E-Commerce , the most important things are innovation and understanding what customer wants. Now-a-days the ease of using ecommerce encourages the customers to buy using ecommerce. It runs on the basis of innovation having the ability to enthral the customers with the products, but with such a large raft of products leave the customers confused of what to buy and what not to. According to business , a company may create three segments like High ( Group who buys often , spends more and visited the platform recently ) , Medium ( Group which spends less than high group and is not that much frequent to visit the platform) and Low (Group which is on the verge of churning out ). This is where Machine Learning provides a crucial solution , several algorithms are applied for revealing the hidden patterns in data for better decision making. In this paper we proposed a Customer segmentation concept in which the customer bases of an establishment is divided into segments based on the customers’ characteristics and attributes. This idea can be used by the B2C companies to outperform the competition by developing uniquely appealing products and services and make it reach to potential customers. This approach is implemented using “k-means”, an unsupervised clustering machine learning algorithm.