<![CDATA[Rice (Oryza sativa L.) is an important food source consumed by more than half of the world's population. In Indonesia, rice plays a major role in providing food for the people. With a large population, Indonesia faces great challenges in meeting the food needs of its population. As the demand for rice increases every year, yield prediction is needed to plan plantings that can fulfill food needs. To improve rice yield through prediction, this process is done by considering various factors such as planting area (ha), urea, sp-36, za, npk, organic, npk formula, yield, and number of seeds. This research uses the CART method to build a web based application that helps the evaluation process. With CART, the data is divided into two parts, namely training data (100 samples) and test data (45 samples), with a division proportion of 70:30%. The implementation of this web application resulted in the classification of rice yields into two categories: low yield and high yield. The confusion matrix results of this classification show an accuracy value of 75%, recall 80%, precision 60%, and f1-score 68%. The CART algorithmproved to be good enough in predicting rice yields and worth using for classification.]]>
Copyrights © 2024
