Prediction of student delay impact on achievement at smk telkom lampung using artificial neural network

Abstract

Student delays are a significant concern that can detrimentally affect the learning process and academic achievement. To address this challenge, leveraging artificial intelligence (AI) technology for analyzing educational data becomes imperative for the early identification of students potentially experiencing delays. In this regard, artificial neural networks (ANNs) emerge as highly relevant and effective methods. ANNs, inspired by the structure and function of the human brain, comprise interconnected artificial neurons capable of learning from input data to generate complex outputs, such as predictions of student delays. This study aims to forecast student delays at Telkom Lampung Vocational High School (SMK) using the ANN method, comparing its performance with other techniques like Support Vector Machine (SVM). Primary data, totalling 4939 instances with 550 cases, 26 features, and 4 meta-attributes, were collected from SMK Telkom Lampung. Performance evaluation encompassed various metrics including Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2). Additionally, a comparative analysis of model performance through scatter plots and box plots was conducted. The research findings suggest that the Neural Network model slightly outperforms the Support Vector Machine model, exhibiting lower prediction error rates and a superior ability to elucidate data variability.