Deep Learning for Predicting Academic Performance: A Machine Learning Approach

Rosario Vargas-Roncal; Adam Abimael Francisco-Paredes; Inés Eusebia Jesús-Tolentino; Jimmy Grover Flores-Vidal; Belia Alida Tucto-Porras; Betsy Luz Quispe-Osorio

doi:10.57239/PJLSS-2025-23.1.00486

Author(s)

Rosario Vargas-Roncal NA

Adam Abimael Francisco-Paredes NA

Inés Eusebia Jesús-Tolentino

Jimmy Grover Flores-Vidal NA

Belia Alida Tucto-Porras NA

Betsy Luz Quispe-Osorio NA

Abstract

This study explores the use of deep learning models to predict students' academic performance, an area of growing interest in education. The importance of the research lies in improving teaching processes by implementing technologies that enable more accurate predictions of students' performance, thus optimizing educational intervention. The research gap is found in the limited application of predictive models in real educational contexts, particularly in secondary and higher education settings. The study's objective is to apply machine learning techniques, such as neural networks and support vector machines, to predict students' academic performance using variables like academic history and demographic data. The methodology employed is based on quantitative analysis of data collected from student surveys, with the use of advanced algorithms for processing and prediction. Key findings indicate that machine learning models have a high degree of accuracy in predicting academic performance, allowing for early identification of students at risk of underperforming. The conclusions suggest that these models can be valuable for personalized teaching and early intervention.

Publication Details

Page(s) 6249-6256

DOI 10.57239/PJLSS-2025-23.1.00486

Published Journal: Pakistan Journal of Life and Social Sciences, Volume: 23, Issue: 1, Year: 2025

Request the full text from PASTIC

Keywords

Student, Educational technology, Machine learning, Prediction, Deep learning, Performance, academic, *Corresponding Author

References

Rodríguez Álvarez,R. Álvarez .2020 .Predicción del rendimiento académico en las Matemáticas de la educación secundaria mediante redes neuronales. net/20.500.14468/14748, : .

Burman I.,Som S. .2019 .Predicting students academic performance using support vector machine. Proceedings - 2019 Amity International Conference on Artificial Intelligence (AICAI), : 756-759.

. .Per formance_Using_Support_Vector_Machine. , : .

Canagareddy D.,Subarayadu K.,Hurbungs V. .2019 .A machine learning model to predict the performance of university students. , : 29.

Chollet F. .2021 .Deep learning with Python (2nd ed. Manning Publications., : .

Goodfellow I.,Bengio Y.,Courville A. .2016 .Deep learning. , : .

Kingma D. P.,Ba J. .2015 .Adam: A method for stochastic optimization. arXiv preprint arXiv:1412, : 6980.

Liu L. .2020 .Deep learning techniques and applications. , : .

Ng A. Y. .2004 .Feature selection, L1 vs. L2 regularization, and rotational invariance. Proceedings of the twenty-first international conference on Machine learning., : .

Nwankpa C.,Ijomah W.,Gachagan A.,Marshall S. .2018 .Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811, : .

Bedia Pérez,Rojas Segovia C. A.,L. E. C. A. .2020 .Diseño de un sistema para predecir la deserción de los alumnos mediante machine learning en la Universidad Tecnológica del Perú. , : .

Puarungroj W. .2018 .Predictive analytics for student performance: A machine learning approach. International Journal of Educational Technology in Higher Education, 15(1) : 25-35.

Ruder S. .2016 .An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609, : 04747.

Segura J. .2018 .Impacto del aprendizaje automático en la predicción del rendimiento académico. Journal of Education and Data Science, 12(3) : 45-67.

Srivastava N.,Hinton G.,Krizhevsky A.,Sutskever I.,Salakhutdinov R. .2014 .Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1) : 1929-1958.

Tieleman T.,Hinton G. .2012 .-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning, 4(2) : 26-31.