<![CDATA[Prediction classification accuracy is a measure of success and satisfaction in predicting past data to produce accurate predictions, knowing how precise a classification pattern predicts class data from future data. In practice, artificial neural networks test the accuracy of a classification pattern using data testing, while to find the pattern itself, use training data. Errors in determining the composition of the presentation of training and testing data can affect the accuracy value obtained, therefore the distribution of the presentation of the amount of data from a dataset is one of the determining factors for the amount of accuracy. This study uses a dataset of Michigan Computer English Course students in 2018-2019 using the Resilient Backpropagation (RProp) method. The data processed was 100 student data for 2018-2019. By dividing the composition of 25% training data with 75% data testing with an accuracy value of 99.25% while dividing 50% training data with 50% data testing with an accuracy value of 100% as well as dividing 75% training data with 25% data testing with a value 100% accuracy.]]>
Copyrights © 2022
