Water is important for survival. With increasing cases of water quality deterioration, it is need of the hour to use brimming machine learning technologies which can aid in water quality prediction and further classification of it into fit or unfit. Traditional WQI methods used are highly data-dependent. Using machine learning algorithm leverages such issues as ML algorithms can adapt according to data and learn from various sources. Various boosting algorithms such as regression, boosting algorithm, optimization algorithms can be used to improve accuracy and feature selection. Reliability also depends on data preprocessing methods, and novel H2O AutoML ensemble model using KNN imputation method has been proven to be more accurate. The accuracy achieved by H2O AutoML is 95.29% (balanced data) and 96.9% in imbalanced data.