PERBANDINGAN ALGORITMA RANDOM FOREST DAN ARTIFICIAL NEURAL NETWORK UNTUK DATASET WATER POTABILITY

Abstract

 Water is an important element that is a basic need for the survival of all living things. Currently, public awareness about the importance of good quality water is increasing. This is due to a wider understanding of the health impacts of unclean water. Water that is clean and safe to use not only has a positive impact on our health, but also on various aspects of daily life. Therefore, research on the quality and suitability of water for consumption is very important. The aim of this research is to determine the best method for comparing water quality for suitability for consumption. This research compares two machine learning methods, namely Random Forest and Artificial Neural Network (ANN) based on attributes for the suitability of drinking water, namely: PH, hardness, solids, chloramines, sulfate, conductivity, organic carbon, trihalomethanes, turbidity and potability. The research results show that the Random Forest algorithm has an accuracy rate of 67.823%, while the Artificial Neural Network (ANN) algorithm achieves an accuracy of 61.014%. From these results, it can be concluded that the Random Forest algorithm has higher accuracy compared to Artificial Neural Network (ANN).