A Weakly Supervised Learning Approach to Anomaly Detection on Cloud Server Configuration

Cloud computing platforms have become increasingly popular across various industries, offering publicly accessible computing, storage, and network solutions to meet the demands of building, scaling, and managing applications. A critical component of these platforms is the recommendation system, which significantly influences customer experience and platform revenue. However, variations in customer behavior and product attributes result in different recommendation scenarios across platforms. One key scenario faced by customers of cloud computing platforms is configuration selection. In this paper, we present an innovative approach to detect potentially misconfigured cloud servers in such scenarios. Our method utilizes weakly supervised learning, using server lifetime as a weak signal to guide the configuration anomaly detection model. By implementing this configuration check, we can prevent customers from purchasing misconfigured products, thus promoting a stable and satisfactory relationship between cloud computing platforms and their customers.