Cloud Service Prediction Using KCFC Approach
Cloud computing is an emerging paradigm where the user can benefit many efficient services. Since many services resemble the same functionality, the user faces relevant and un-relevant information as data burden. So, Recommender System (RS) is getting used to suggest the user only the information that suits their search. Here (CFC)-Collaborative Filtering Coefficient is used as RS which functions by analyzing user history and similar service from neighbor users. Pearson coefficient is used to calculate the association between the services. But, it works for existing users not for new users because the further user details are not sufficient to recommend a service. To overcome this, the KNN approach is utilized to classify the recommendation from a k-nearest neighbor by finding the resemblance between various client ratings using Euclidean Distance measure. Thus, the KNN-CFC hybrid novel approach can create a new efficient RS framework which supplies the client a most relevant service information with low execution time for various data densities and different users and services.
KeywordsQuality of service k-Nearest Neighbour CFC-Collaborative Filtering Coefficient Pearson coefficient Recommendation system
- 3.Wang, S., Zhao, Y., Huang, L., Xu, J., Hsu, C.H.: QoS prediction for service recommendations in mobile edge computing. J. Parallel Distrib. Comput. (2017)Google Scholar
- 12.Kumar, S., Pandey, M.K., Nath, A., Subbiah, K., Singh, M.K.: Comparative study on machine learning techniques in predicting the QoS-values for web-services recommendations. In: 2015 International Conference on Computing, Communication & Automation (ICCCA), pp. 161–167. IEEE, May 2015Google Scholar