CAHPHF: Context-Aware Hierarchical QoS Prediction with Hybrid Filtering

Article Type

Research Article

Publication Title

IEEE Transactions on Services Computing


With the proliferation of Internet-of-Things and continuous growth in the number of web-services at the Internet-scale, service-recommendation is becoming a challenge nowadays. One of the prime aspects influencing the service-recommendation is the Quality-of-Service(QoS) parameter, which depicts the performance of a web-service. In general, the service provider furnishes the QoS values before service deployment. In reality, the QoS values of service vary across different users, time, locations, etc. Therefore, estimating the QoS value of service before its execution is an important task. Thus, QoS-prediction has gained significant attention. Multiple approaches are available in the literature for predicting QoS. However, these approaches are yet to reach the desired accuracy level. Here, we study the QoS-prediction problem across different users and propose a novel solution by considering the contextual information of both services and users. Our proposal includes two key-steps: (a)hybrid-filtering, (b)hierarchical-prediction-mechanism. On one hand, the hybrid-filtering aims to obtain a set of similar users and services, given a target user and a service. On the other hand, the goal of the hierarchical-prediction-mechanism is to estimate the QoS value accurately by leveraging hierarchical-neural-regression. We evaluated our framework on WS-DREAM datasets. The experimental results show our framework outperformed the major state-of-the-art approaches.



Publication Date



Open Access, Green