It is important that the wireless network is well managed, optimized and planned, using the limited wireless spectrum resources, to serve the explosively growing traffic and diverse applications needs of end users. Considering the challenges of dynamics and complexity of the wireless systems, and the scale of the networks, it is desirable to have solutions to automatically monitor, analyze, optimize, and plan the network, instead of the traditional way of engineers manually monitoring, analyzing, tuning, and planning the network. This article addresses the limitations of existing network optimization and planning technologies by providing approaches and solutions of data analytics and machine learning (ML) powered optimization and planning. The approaches include analyzing some important metrics of performances and experiences, at the lower layers and upper layers of open systems interconnection (OSI) model. The approaches include deriving a metric of the end user perceived network congestion indicator. The approaches also include monitoring and diagnosis such as anomaly detection of the metrics, root cause analysis for poor performances and experiences. The approaches also include enabling network optimization with tuning recommendations, directly targeting to optimize the end users experiences, via sensitivity modeling and analysis of the upper layer metrics of the end users experiences v.s. the improvement of the lower layers metrics due to tuning the hardware configurations. The approaches also include deriving predictive metrics for network planning, and modeling of traffic demand distributions and trends, incentives of traffic gains if the network is upgraded, etc. The models detect and predict the suppressed engagement or suppressed traffic demand. These approaches of optimization and planning may provide more accurate detection of optimization and upgrading/planning opportunities for cells at a large scale, enable more effective optimization/planning of networks, such as tuning cells configurations, upgrading cells’ capacity with more advanced technologies or new hardware, adding more cells, etc., improving the network performances and providing better experiences to end users of the networks. of sensitivity analysis is the prediction would give out a predicted improvement of metric Y, if metric X is improved by a certain amount. This provides opportunities and advantages to do proactive optimization, with predicted upper layer end-users’ experiences.