Human beings are dependent on the natural resources that stands for its quality. Climatic changes and environmental impacts have always been under observation. The quality of the products is always measured before use. Water, an inevitable resource ,has got a serious significance in checking its quality due to the influence of various external factors like industrial effluents, acid rain etc. This paper provide same theology for assessing the water quality that uses statistical quality control technique and Machine Learning algorithms to scale up the classification accuracy. The classification is focused on deciding if the water is suitable for drinking purpose. The goal of this study is to develop a water quality prediction model with the help of water quality factors using Artificial Neural Network (ANN) and time-series analysis.

Different toxins have been imperiling water quality over the past decades. As a result, foreseeing and modeling water quality have gotten to be basic to minimizing water contamination. This inquiry has created a classification calculation to foresee the water quality classification (WQC). The WQC is classified based on the water quality file (WQI) from 7 parameters in a dataset utilizing Back Vector Machine (SVM) and Extraordinary Gradient Boosting (XGBoost). The comes about from the proposed model can precisely classify the water quality based on their features. The inquire about result illustrated that the XGBoost model performed way better, with an exactness of 94%, compared to the SVM demonstrate, with as it were a 67% exactness. Indeed way better, the XGBoost brought about in as it were 6% misclassification mistake compared to SVM, which had 33%. On best of that, XGBoost too gotten consistent predominant comes about from 5-fold approval with an normal accuracy of 90%, whereas SVM with an normal exactness of 64%. Considering the upgraded execution, XGBoost is concluded to be superior at water quality classification.