Wireless communication is a fundamental part of our everyday lives, powering everything from mobile phones to smart home devices. However, one of the ongoing challenges in this field is ensuring that networks provide consistent and reliable coverage, especially in busy or complex environments like cities. Traditional methods of network planning often fall short in addressing the ever-changing demands and obstacles, such as varying user densities, interference, and signal loss in urban areas. This thesis delves into how machine learning (ML) can be used to tackle these challenges and improve wireless network coverage. By employing ML algorithms, we can monitor real-time network conditions, predict how the network will perform under different scenarios, and adjust optimize coverage dynamically. The literature review highlights cutting-edge ML techniques that are currently being used to make networks more efficient, with a particular focus on improving how devices switch between network towers (handover processes), how resources are allocated, and where antennas are best placed. Our approach uses simulations to model an urban environment, considering the varying population densities and infrastructure complexities that one might find in a typical city. We randomly position base stations and users within this simulated grid and use signal propagation models to measure important performance indicators, such as Received Signal Strength Indicator (RSSI) and Signal-to-Noise Ratio (SNR). These measurements are then used to train ML models using optimization techniques like reinforcement learning. To ensure the reliability of our results, we rigorously test the performance of these models through robust validation methods. The results of our study suggest that ML-based strategies can significantly improve how wireless networks are optimized, leading to more adaptive and efficient coverage. This not only enhances the user experience but also opens the door to smarter, more responsive network management in the wireless technologies of the future.