Service Association Factor (SAF) for Cloud Service Selection and Recommendation

Authors

  • Imran Mujaddid Rabbani Dept. of Computer Science and Engineering, University of Engineering & Technology
  • Muhammad Aslam
  • Ana Maria Martinez Enriquez
  • Zeeshan Qudeer

DOI:

https://doi.org/10.5755/j01.itc.49.1.23251

Keywords:

Service Selection, Recommendation Systems, Association Factor, Interrelationships

Abstract

Cloud computing is one of the leading technology in IT and computer science domain. Business IT infrastructures are equipping themselves with modern regime of clouds. In the presence of several opportunities, selection criteria decision becomes vital when there is no supporting information available. Global clouds also need evaluation and assessment from its users that what they think about and how new ones could make their selection as per their needs. Recommended systems were built to propose best services using customer's feedback, applying quality of service parameters, assigning scores, trust worthiness and clustering in different forms and models. These techniques did not record and use interrelationships between the services that is true impact of service utilization. In the proposed approach, service association factor calculates value of interrelations among services used by the end user. An intelligent leaning based recommendation system is developed for assisting users to select services on their respective preferences. This technique is evaluated on leading service providers and results show that learning base system performs well on all types of cloud models.

Author Biography

Imran Mujaddid Rabbani, Dept. of Computer Science and Engineering, University of Engineering & Technology

PhD Scholar

Downloads

Published

2020-03-25

Issue

Section

Articles