<![CDATA[Predicting students' academic performance is crucial in enhancing the quality of education in higher institutions. This study aims to develop a model for predicting student grades based on academic history using Artificial Neural Networks (ANN) with the backpropagation method. Academic data and supporting variables from students are used as inputs in the model, which aims to forecast future academic achievements. In this research, the ANN was structured with a layered architecture consisting of 5 neurons in the input layer, one hidden layer with 7 neurons, and an output layer. The model was trained using the backpropagation algorithm to minimize Mean Square Error (MSE) and improve prediction accuracy. Testing results show that the ANN model achieved convergence with an MSE value of 0.01363 in 68 epochs. Based on these findings, the developed model can be utilized by academic advisors to monitor and predict students' academic progress. Overall, this research contributes to providing an effective data-driven tool for academic mentoring processes, supporting higher education institutions in optimizing students' potential for achieving maximal academic success.]]>
Copyrights © 2025
