<![CDATA[Soil fertility on an agricultural land is very influential with agricultural yields, where plants can grow well and fertile if nutrient intake is met. The purpose of this research is to improve the accuracy in predicting soil fertility by utilizing machine learning by combining two classification algorithms using soft voting methods in the classification of agricultural land fertility. In this research, one of the ensemble learning methods called soft voting is employed. Soft voting is used to enhance accuracy by optimizing the combination of algorithms based on the highest probability provided by each model. The Gaussian Naive Bayes algorithm is used to predict classes in the sample data based on the Gaussian distribution of numerical data, while the decision tree is utilized to predict classes by constructing a decision tree using soil content attributes for the classification of fertile or infertile soil. The use of the Gaussian Naive Bayes algorithm in identifying fertile and infertile soil based on existing attributes achieved an accuracy rate of 87.2%. The decision tree algorithm, based on decision tree modeling, helped identify important attributes for decision-making with an accuracy rate of 88.3%. The soft voting method played a crucial role in improving accuracy by combining both algorithms, resulting in an accuracy rate of 88.8%. Based on the accuracy results obtained, the use of soft voting optimization in predicting soil fertility has the highest accuracy because it combines the Gaussian naïve bayes algorithm and the decision tree algorithm.]]>
Copyrights © 2024
