<![CDATA[Classification algorithms are crucial in developing predictive models that identify and classify soil fertility levels based on relevant attributes. However, optimizing classification algorithms presents a major challenge in enhancing the accuracy and effectiveness of these models. Therefore, this research aims to optimize the classification algorithm in soil fertility analysis using ensemble learning techniques, specifically Soft Voting Ensemble. This research method is designed to understand soil fertility levels in modern agriculture by comparing the performance of various classification algorithms and ensemble approaches. Using a dataset from the Purwodadi Department of Agriculture, this study examines the optimization of algorithm parameters such as Random Forest, Gradient Boosting, and Support Vector Machine (SVM) and the implementation of Soft Voting Ensemble. Before applying Soft Voting Ensemble, each algorithm was evaluated with the following results: Random Forest achieved an accuracy of 90.93%, precision of 91.08%, recall of 90.33%, and F1-Score of 90.70%; Gradient Boosting achieved an accuracy of 91.53%, precision of 91.19%, recall of 91.56%, and F1-Score of 91.38%; SVM achieved an accuracy of 88.91%, precision of 89.66%, recall of 87.45%, and F1-Score of 88.54%. After implementing Soft Voting Ensemble, the accuracy improved to 91.63%, with an average precision of 91.21%, recall of 91.77%, and F1-Score of 91.49%. This study divided the data into 80% for training data and 20% for testing data. These findings indicate that the Soft Voting Ensemble has the potential to enhance agricultural productivity and sustainability.]]>
Copyrights © 2023
