<p>In several urban industrial regions affected by air pollution, it is crucial to monitor air quality in order to improve the quality of life and prevent any damage to health. This paper mainly focuses on the prediction of air quality index (AQI) using two different machine learning algorithms SVM and KNN. In recent times, machine learning has become widely popular and relevant in the forecasting of AQI because of its ability to work with large datasets and provide highly accurate conclusions from raw data. This study helps in analyzing several international research works which helps in better understanding of the forecasting power of algorithms used and the predicted outcomes provide insights into the air quality which aid authorities in decision making. Our analysis shows that hybrid models, created using multiple algorithms, outperform traditional models involving a single algorithm. Moreover, the usage of larger datasets to train the models led to more accurate results.</p>