Classifier models are actively being brought into use in various fields to chart out future possibilities. When it comes to values like the Air Quality Index that directly affect human lives, accuracy is a must. Air pollution claims around 4.2 million lives per year, according to the World Health Organization. Inaccurate predictions in such fields can be detrimental to the environment as well as general public health. However, the accuracy of these classifier models can be affected by how the given data is processed and the presence of outliers. The outliers can considerably alter the results of these classifier models. Hence, the aim of this project was to study the effects of the presence and absence of outliers in a dataset on the prediction accuracy of various classifier models and find the most accurate classification model among the ones that were tested

.