A Machine Learning - Based System for Determining Water Potability

This research focuses on enhancing water potability classification through the integration of three machine learning techniques. A comparative analysis of diverse classification methods is conducted, incorporating multiple thresholds by employing a variable extraction approach. The primary objective is to streamline the input set, aiming for a significant reduction in computational costs and model complexity. This streamlined approach not only facilitates a more efficient training process but also implies a shorter duration for model training. To rigorously evaluate the model’s performance, a K-fold cross-validation is implemented within this framework. This comprehensive approach contributes to the advancement of water quality assessment methodologies, with potential implications for improving the efficiency and reliability of potability water classification models.