<![CDATA[Classification of the appropriateness of equipment in the laboratory is needed by university management to determine future laboratory development steps. The suitability of laboratory equipment can be influenced by various factors, so it is necessary to know which variables are crucial in influencing the condition of the laboratory equipment's suitability. Data mining techniques can be used to explore new knowledge so that it can produce appropriate laboratory equipment. Some algorithms that can be used are K-Nearest Neighbord and Naive Bayes. The aim of this research is to compare the level of optimization of two methods in classifying the suitability of Chemistry laboratory equipment at FMIPA Unand using the K-Nearest Neighbor and Naive Bayes methods. The attributes used are year of procurement, level of use, level of damage, length of use of the tool, and condition of tool accessories. The data used is Materials Chemistry laboratory equipment, FMIPA, Andalas University from 2010-2023 with a total of 105 data. The research results show that the accuracy level of the Naive Bayes Method is better than the K-Nearest Neighbor Method. This is proven by the results of the Rapidminer test, which obtained the highest accuracy of 94.74% at a total testing data of 30% of the total data, while for the K-Nearest Neighbor method, the highest accuracy was obtained at 79.03% at a total testing data of 50% of the total data. It is hoped that the results of the tool classification can serve as guidance and evaluation to support the development of the FMIPA Chemistry laboratory at Andalas University]]>
Copyrights © 2024
