In today’s world, there is an increasing concern over air pollution. It is obligatory to monitor the quality of the air, based on the Air Quality Index (AQI), in times like these since the air quality is continuously deteriorating. Enhancing the ability to monitor and forecast air quality encourages individuals to make informed decisions concerning outdoor activities, thereby mitigating the potential exposure to harmful pollutants. This paper was undertaken to examine the utilization of machine learning models to the prediction of AQI values. The proposed model aims to examine 11 different meteorological parameters that influence the air quality in a given geographical setting. The degree to which these factors directly impact human health and welfare determines their significance. After the required preprocessing, three classification models are applied and evaluated to train and test the dataset to predict the AQI for the city of Pune. After conducting extensive analysis, it was concluded that for the given dataset, the Random Forest Classifier gives the least Mean Square Error (MSE).