Abstract: It is a service recommender system for providing appropriate recommendations to users. In the last decade, the number of customers, services as well as online information has grown rapidly. So, the big data analysis for service recommender systems is required. As a result, traditional service recommender systems often suffer from scalability and inefficiency problems when analysing such BigData. The vital thing is, most of existing service recommender systems present the same ratings of services to different users without considering previous user’s preferences, and hence fails to meet user's personalized requirements. We will propose a method called “Keyword-Aware Service Recommendation”, i.e. KASR, to fulfil the above challenges. In our system Keywords are used to indicate user's preferences. In very first stage data sets will be created for given system. Also user-based Collaborative Filtering algorithm is used to generate appropriate recommendations. KASR is implemented on Hadoop, to improve its scalability and efficiency in big data environment, a widely-used distributed computing platform known as MapReduce is used for parallel processing paradigm. At final stage, experiments are concluded on real-world data sets, and results shows that KASR significantly improves the accuracy & scalability of service recommender systems over existing approaches. As explained above we will use the techniques such as Map Reduce for parallel processing paradigm and the algorithm used in our system are Collaborative Filtering algorithm is for generating appropriate recommendations.

Keywords: KASR, ASC, ESC, Personalized rating, BigData, Cloud Computing, Hadoop.