Air pollution is an alarming concern for all nations due to its serious impacts on human health and the environment. Accurate air quality prediction is significant for taking the required preventive measures, especially for individuals who are prone to the risk factors that result from unhealthy air quality. Until now, several approaches have been developed to forecast the Air Quality Index (AQI), such as the overview of machine learning-based techniques to quantify the concentration of chemicals in the air that result in the air quality index. In this study, we developed several machine learning models, including tree-based algorithms, deep learning sequence models, and traditional approaches, to predict PM10 concentrations. The performance of these models using key evaluation metrics to determine their effectiveness in forecasting air quality was compared and analyzed. Additionally, we built an interactive web application that showcases the models' training and testing results, with visualizations to better interpret predictions and model performance.