D. J. Hemanth
Abstract
Recommendation systems have become a vital area of research in recent times. These recommendation systems are very much needed for e-commerce applications to identify the products liked by a customer which helps the companies to promote product sales and improve their product quality. It also helps the users to arrive at the purchasing decision without reading the online reviews about the product. The key idea behind the proposed work is to analyze the user preference for the products from the online data by employing the collaborative filtering based recommendation framework. The concept of collaborative filtering is best suited for recommendation systems involving a large set of product users. It generates a user-item matrix and finds the list of products liked by the individual users. It gives prediction regarding the product that a user could buy in the future and also recommends the products which are liked by the customers who have similar interests. It gives a comparative analysis in terms of performance metrics and accuracy of different collaborative filtering techniques.
Keywords: Recommendation Systems, Sentiment Analysis, Collaborative Filtering, Machine Learning
**View Full Paper in the Springer Source.