Performance Evaluation of Naive Bayes Algorithm for Classification of Fertilizer Types

Determining the right fertilizer is very important to get optimal plant growth results. Each plant requires different nutrient requirements. Different soil types cause the soil's nutrient content and PH value to differ from one type to another. Regional conditions in a place will also cause the need for plant absorption of nutrient content to be more varied. By using the classification of the problems that have been mentioned, it can be solved by studying patterns from existing fertilizer use data into knowledge that can be used to determine decisions. In this study, modeling with the Naïve Bayes algorithm has been applied to the existing fertilizer use data where the probability value of each class has been calculated to get the highest probability value of a class. The measurement of the accuracy value of the modeling used is measured using the Split Validation method, where the training data will be divided into training data and testing data so that the accuracy value of the model is obtained. From the applied modeling, an accuracy value of 60% is obtained, which shows the level of accuracy of the model obtained from the classification results in the form of the name of the fertilizer, which is expected to help in determining the name of the fertilizer that needs to be used.