Use of decision trees for water quality assessment: analysis of key parameters

Abstract

The paper investigates the application of the decision tree method for analyzing and predicting water quality. The main objective of the study is to identify the key physical and chemical parameters that affect the potability of water. The Decisive Tree Method is used to create a model capable of classifying water as suitable or unsuitable for drinking. The results of the study showed that the decisive trees model achieved an accuracy of 62.03% and F1 Score of 0.5292. The most important parameters affecting the model predictions include sulfate content, pH and water hardness. The error matrix and feature importance plot provided valuable information to further improve the model and understand the effect of different parameters on water quality.