Cloud computing is becoming popular. Building high-quality cloud applications is a critical research issue. QoS rankings give valuable data for making optimal cloud service selection from a set of functionally equivalent service candidates. To get QoS values, t real-world invocations on the service applicants are usually required. To avoid the time-consuming and expensive real-world service invocations, this project proposes a QoS ranking prediction system for cloud benefits by exploiting the past service utilization encounters of different consumers. Our proposed system requires no additional invocations of cloud administrations when making QoS positioning expectation. Two customized QoS positioning expectation approaches are proposed to foresee the QoS rankings directly. Comprehensive experiments are led utilizing real world QoS information, including 300 distributed clients and 500 real world web benefits everywhere throughout the world. The experimental results about demonstrate that our methodologies beat other competing approaches.