The present study shows a comprehensive study on the prediction of apparent temperature, a critical metric in assessing human comfort and health, using a large dataset comprising various meteorological parameters including temperature, humidity, wind speed, and visibility along with the corresponding data collected over a considerable period. The use of advanced machine learning techniques and accurate models enhances the understanding of variability of these weather parameters under diverse weather conditions. The research commences with the analysis of the dataset to identify the key parameters affecting the apparent temperature. Parameters such as wind speed, humidity, and precipitation type are used for their significant impact on temperature. Machine learning algorithms are used to construct robust and effective prediction model through rigorous experimentation and evaluation for accurate forecasting of apparent temperature. The model also evaluates relative importance of the parameter by considering various input combinations of features. Furthermore, investigation of temporal and spatial variations in apparent temperature is done for different patterns that are important for regional climate studies and urban planning. This research shall emerge as a stepping stone to ensure public safety and emergency response. A deeper understanding of apparent temperature dynamics can provide time for preparation to reduce the impacts of changing weather in the future.