IMPLEMENTATION OF THE BACKPROPAGATION METHOD FOR RECOMMENDING ANNUAL AWARD RECIPIENTS AMONG OUTSTANDING STUDENTS

This research aims to develop a recommendation system for annual awards for outstanding students using the Backpropagation method in an Artificial Neural Network (ANN). Student assessment is based on four main variables: academic grades, attitude scores, extracurricular activity scores, and attendance records. The data were obtained from an elementary school in Pasuruan City through a survey method, then processed using preprocessing and normalization techniques before being trained using the Backpropagation algorithm. The model was developed using a Sequential architecture with two hidden layers, and its performance was evaluated using a confusion matrix and a classifi-cation report. The testing results showed that the model was able to classify outstanding students with a highest accuracy rate of 97%, demonstrating strong performance in terms of precision, recall, and F1 score. These results indicate that the Backpropagation method is effec-tive in enhancing the objectivity and efficiency of the outstanding stu-dent selection process based on historical data.