<![CDATA[To facilitate every decision making in the process of purchasing plastic injection material in the sales department of PT. Surya Technology Industri, which has not been controlled with production or sales to customers, resulting in too much stock and cannot be sold. PT. Surya Technologi Industry, which is engaged in Manufacturing, has more than 400 types of raw materials so that companies find it difficult to predict future needs and what the company needs. The aim of this research is to analyze the data for purchasing plastic injection materials for more accurate and efficient results. Data mining techniques with the Naïve Bayes algorithm method are used in this study to classify so as to produce decisions with probability values and useful rules as input in determining the decision-making process. Of the 1120 datasets on the purchase of plastic injection material, testing was carried out ten times, the distribution of the test with different training data and testing data with the provisions of 10% test data and 90% training data. Based on the results obtained, it shows that the Naïve Bayes algorithm in classifying data on the purchase of plastic injection materials using the Rapid Miner tools has the highest accuracy, precision and recall values, namely testing at the proportion of 90% (1008 data) training and 10% (112 data) testing using cross validation 10-fold with 88.93% accuracy, 92.88% precision and 87.77% recall. This shows that the Naïve Bayes algorithm has a fairly good performance in making predictions so that it can be implemented for the decision- making process for the company. Keywords : Naïve Bayes Algorithm, Data Mining, RapidMiner, Classification]]>
Copyrights © 2020
