We discuss the application of Machine Learning to the task of optimization of Quality of Service (QoS) parameters. The Powerpoint Presentation here is heavily redacted to protect Qualcomm’s IP. We delve into the challenges faced during the optimization process such as the uneven weights given to the parameters across the various use-cases and how they were dealt with. Furthermore, we discuss the Automation Framework implemented in Python to simulate these use cases in Android 10 along with the upgrades made. Finally, we talk about the LSTM architecture used for the prediction of the priorities that allowed us to optimize these QoS parameters.