 This research paper examines the use of a supervised machine learning model, a multi-layer perceptron, MLP, for anomaly detection in microservices. The authors created a microservices infrastructure, developed a fault injection module to simulate application level and service level anomalies, collected a system monitoring dataset, and then validated the MLP model's ability to detect anomalies. The results showed that the MLP model was able to detect anomalies in both domains with higher accuracy, precision, recovery, and F1 scores than other methods. Additionally, the authors found that the MLP model could be used to monitor service level metrics such as service response times, which has the potential to provide more effective distributed system monitoring and management automation. This article was authored by Joao Nobra, E. J. Soltero Pires, and Arsenio Riz.