Web service has been emerged as a promising technique to support inter-operable machine-to-machine interaction which provides a method of communication between electronic devices over a network. As the number of web services with similar functionality has increased rapidly over the internet the web service discovery is not a challenging task but selection and recommendation are becoming more important. The Optimality of a web service depends on its performance and performance is measured through Quality of Service that is QoS. QoS is the set of non-functional properties of a web service which includes response time, price, failure rate and so on. Recommendation system initially searches for the list of web services those having similar functionality, which the user requested and finally the optimal web services are recommended to users. In addition, QoS is widely employed in describing non-functional properties of Web Services for optimizing the Web service composition. Since the number of functionally equivalent services offered on the web with different QoS properties is increasing, it is quite important to recommend services considering their non-functional QoS properties. In this project, we can include the recommendation algorithm which includes ratings, reviews, and emoticons. These details are recommended by using a hybrid algorithm. User details are encrypted using Elliptical curve cryptography. Third parties are difficult to hack the original details. Admin can discover the services based on the highest feedbacks and also recommended based on locations. And also using roll back discovery to cancel the web services automatically to overcome the burden of service cancellation.