<p>Air pollution is a significant environmental concern, especially in urban areas with dense populations. Long-term exposure to air pollution can cause serious health problems, such as respiratory diseases, cardiac problems, and even premature mortality. Reducing air pollution is essential for protecting human health and the environment. This paper aims to predict air quality in National Capital Territory (NCT) of Delhi, India using machine learning algorithms, specifically focusing on the Random Forest model. Air pollution is a significant environmental concern, particularly in densely populated urban areas like NCT Delhi India. It involves the contamination of the atmosphere with hazardous substances such as Particulate Matter (PM_2.5, PM₁₀), Nitrogen Dioxide (NO₂), and Sulfur Dioxide (SO₂). In our research, we proposed a machine-learning framework using random forest algorithms to predict air quality. We used hourly measurements of key pollutants from January 2017 to December 2018 in the NCT Delhi India region, with predictions evaluated through k-fold cross-validation and grid search techniques. Our findings revealed that the Random Forest regression model outperforms simpler models, achieving an R² value of 98.89, highlighting its efficacy in capturing complex relationships among air quality parameters. The random forest model can be utilized by policymakers to make informed decisions regarding the management and regulation of air quality.</p>