WSRank: A Collaborative Ranking Approach for Web Service Selection

As Cloud Computing has emerged as new computing paradigm, more and more services have been deployed and provided on the cloud platform with a SaaS model, thereby how to select a qualified service is becoming a key issue. Several approaches based on service feedback ranking e.g., rating-oriented collaborative filtering (CF) have been proposed. Traditional CF approaches predict the potential QoS values that a user would assign to unused services, so that service candidates are mainly ranked with the predicted values. In this paper, we present WSRank, a novel ranking-oriented CF approach that addresses the service ranking problem through directly modeling user preferences derived from past QoS values. Different from the existing similar approaches, WSRank firstly presents a QoS model which allows users to express their preferences flexibly while providing combination of multiple QoS properties to give an overall rating to a service. Second it measures the similarity between users based on the correlation between their rankings of services rather than the rating values. Experimental results show that our approach outperforms the competing approaches significantly on the AP measure for evaluating ranked results.