The Paper herein, introduces the algorithm and the model of machine learning where Multiple variable linear regression model, support vector machine, K-Means clustering method is used to predict the mean user number depending of some other variables. This analysis will help a market operation and planning team of a telecom network, to design and optimize the network and achieve maximum users under a telecom network. The worst cells which we obtained from the clustering methods will help them to work with the worst cells and solve network issues or capacity issues to get more subscriber to improve their profit. This analysis will help to plan and design cluster by cluster which is also very important for a telecom operator. The final result correctly leads the company to predict the user number of a network, which definitely provides great commercial value and help to build a good and customer-centric mobile network. The predictive models and clustering algorithms provide actionable insights and recommendations for improv- ing network efficiency, QoS, and user satisfaction. Despite the promising results, the research faces several limitations and challenges, including data quality issues, model interpretability, and algorithm scalability. Future research directions may focus on addressing these challenges and exploring new techniques for enhancing predictive accuracy, model explain ability, and computational efficiency