CAHPHF: Context-Aware Hierarchical QoS Prediction With Hybrid Filtering

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