Implementation of the Naïve Bayes Method in Determining the Quality of CPO (Crude Palm Oil)

Abstract

Palm oil is a very abundant source of vegetable oil and produces the highest vegetable oil compared to other plantation crops, which is the background of this research. This study aimed to classify the quality of CPO (Crude Palm Oil) into two classification classes using the Naïve Bayes method. This classification is expected to reduce human error in determining CPO quality. The parameters used in this research are free fatty acid content, moisture content and impurities which greatly affect the quality of CPO. By using the split data technique at the time of validation, the data is divided into training data and test data by 70:30. Based on the results of testing using the confusion matrix, the use of the Naïve Bayes method for data collected on research objects obtained an accuracy rate of 97.7% or included in the excellent category. While the specificity value is 95.8%, the recall value is 100%, and the precision is 95.4%.