Data analytics is a major consideration to build efficient and automated prediction system to the various business needs. Especially many technologies based industries focusing to increase the business growth on offering the right product to right customer at right time. However, despite of various advantageous of data analytics models, clustering customer complaints to online product of the e commerce platform is becoming a vital research in the ecommerce industry. E- commerce is a platform for marketing and promoting the product to online customer. In order to evaluate the opinion of the customers to products purchased using e commerce system is extracted with respect to various challenges and advantages. Extracted opinion of the customer is processed to obtain the intension and behavioural patterns on the statements which express the agreement and disagreement of the product. To reveal the negative or positive feelings of the customer rating, advancement in the information technology is employed with sentiment analysis. Deep Attention Network with long short term memory architecture is proposed in this work to obtain the latent factors of the user to enhance the customer retention. Model is adaptable to temporal and time varying data along its existence of long term dependences between the users. Initially data preprocessing is employed to extract the user profile on analysis of behavioural and psychographic information’s. Preprocessed data is employed for Latent Dirichlet Allocation feature to extract the opinion of the latent user intention on the parsed data and store long dependency of the data in latent representations on the LTSM Model. Latent user intention is projected to the long short term memory for efficient data organizing on indexing as network. Organized data is employed to deep attention network composed of various layer is considered as learning representative which provides valuable forecasting as suggestion and recommendation to products to enhance the customer retention. We evaluate the performance of the proposed deep learning approach on Amazon dataset which considers the reviews of the customer complaints to various products. It has been proved to be outperforming against state-of-the-art methods against precision, recall and F Measure respectively.

E commerce, Customer Complaint, Long short term memory, Deep Attention Network, Latent Dirichlet Allocation, Sentiment Analysis