This study employs multiple machine learning regression techniques to predict air quality indices and conducts a comparative analysis to identify the optimal model based on data efficiency and processing time. The Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) were used as evaluation measures to compare these regression models. Furthermore, the processing time of each algorithm was evaluated through independent training and hyperparameter tuning to determine the best-fit model regarding computational efficiency and error rates. In this paper, we have calculated the custom score which is sum of MAE, RMSE, MAPE and time processing values. The best model obtained is the custom stacked regression model has custom score of 111.41 which is very less as compared to other regression models.