The E-Commerce industry is a new way of shopping. Most manufacturers prefer to sell their products on E-commerce websites because of low maintenance and high returns. This paper highlights the application of data science and deep learning methodologies to drive the E-commerce business. The first part of the paper explains the role of data science to identify potential customers, items recommendations and fraud detections. Different stages of building E-commerce websites and the role of proper handling of data is then highlighted. The second part of the paper is about the use of deep learning approaches like Recurrent neural networks in analysing textual information is presented with a demonstration of three architectures. At last, the importance of convolutional neural networks in the E-commerce industry is presented. Fashion related images like dresses, shoes and bags are classified using two separate convolution neural network architectures.