Downloads: 127 | Views: 203

Survey Paper | Computer Science & Engineering | India | Volume 5 Issue 1, January 2016

A Survey on Smart Service Recommendation System by Applying Map Reduce Techniques

Pallavi R. Desai | B. A. Tidke

Abstract: In the era of internet amount of data grown beyond the capacity of storing and processing, This known as Big Data. When Users deals with Big Data it face varies difficulty at the time of needful data extraction. Their for we purpose Smart Service Recommender system is providing appropriate recommendations to users as per their interest. In the past few years, the amount of online web data has increases explosively, yielding the big data processing and analysis problem for recommender systems. Consequently, most of the traditional service recommender systems frequently suffer from scalability and inefficiency problems when processing or analysing such large volume data. Moreover, an existing service recommender system present the same ratings and rankings of items to different users without considering varied users? preferences, and therefore fails to meet users personalized requirements. This project proposes a Smart Service Recommendation system, to address the above challenges. It aims at presenting a personalized recommendation list and recommending the most appropriate items to the users effectively. Specifically, weights of s are used to indicate users' preferences, and a user-based Collaborative Filtering algorithm is adopted with Opennlp to generate appropriate recommendations. To improve its scalability and efficiency in big data environment, it is implemented on Hadoop, a widely-adopted distributed computing platform for processes large data using MapReduce parallel processing paradigm. Finally, extensive experiments are conducted on real-world data sets, and results demonstrate that Personalize User-Based Recommendation System significantly improves the accuracy and scalability of service recommender systems over existing approaches.

Keywords: Big Data, MapReduce, Hadoop, recommender system, preference,

Edition: Volume 5 Issue 1, January 2016,

Pages: 365 - 369