Delhi city in India is one of the highly urbanized global cities. This book chapter deals with the different machine learning techniques which is used for air quality prediction using the existing data such as particulate matter, gaseous and meteorological parameters. The study provides information about the correlation of the different parameters and the variation in particulate matter concentration between the measured and predicted values. The results showed that the particulate matter concentration varied with changes in levels of different gaseous pollutants, while atmospheric temperature, solar radiance, and wind speed had a minimum influence on particulate matter levels. The study compares three widely used machine learning models for predicting particulate matter (PM2.5 and PM10). The machine learning models used in the study are multiple linear regression (MLR), random forest (RF), and extreme gradient boosting (XGB). The results show that MLR predictions were better than the other two models in terms of accuracy and error metrics. Meteorological factors showed the order of correlation from high to low, which was the temperature > solar radiation> wind speed> relative humidity> rainfall. Among the above meteorological factors, wind speed, rainfall, temperature, and humidity negatively correlate with particulate matter concentration , but the correlation between relative humidity and PM2.5 concentration was found to be positive. The study shows that the air quality in a region is not only source-dependent but also depends on the regional conditions. Examining the conditions may help us to understand and suggest better ways to mitigate air quality issues in different regions.