AI-Based Student Performance Prediction and Academic Recommendation System Using Deep Learning

Author

P. Jai Ruby, A. Paulin

Abstract

 Predicting student academic performance at an early stage is important for identifying students who may require additional academic support. Traditional evaluation methods mainly depend on examination results and manual assessment, which may not consider the combined influence of academic, behavioural, demographic, and life style-related factors. This paper presents an AI-based student performance prediction and academic recommendation system using deep learning to address this need.

The proposed system analyses 19 student-related input features, including study hours, attendance, previous scores, parental involvement, access to learning resources, motivation level, sleep hours, and other relevant factors. The Student Performance Factors dataset is preprocessed by removing duplicate records, handling missing values, encoding categorical features using label encoding, and applying feature scaling. An Artificial Neural Network (ANN)-based deep learning model is developed to predict the student's examination score. The model is evaluated using Mean Absolute Error (MAE) and the coefficient of determination (R²).

The experimental results recorded for the developed model show an MAE of 0.97 and an R² score of 0.70 on the testing dataset. Based on the predicted examination score, the system generates an academic grade and provides recommendations to support student improvement. The application is developed using Python Tkinter, which provides a graphical user interface for entering student details and viewing prediction results. SQLite database integration is used to maintain prediction history for future reference.

The proposed system combines performance prediction, grade generation, academic recommendations, and result management within a single application. It demonstrates the potential of deep learning as a supportive tool for educational performance analysis and academic decision-making.

Keywords

Artificial Intelligence, Deep Learning, Student Performance Prediction, Artificial Neural Network, Educational Data Mining, Academic Recommendation.

Full Text:

Download Paper PDF

References

[1] M. Yağcı, “Educational data mining: Prediction of students’ academic performance using machine learning algorithms,” Smart Learning Environments, vol. 9, article 11, 2022. doi: 10.1186/s40561-022-00192-z.

[2] M. H. Bin Roslan and C. J. Chen, “Educational data mining for student performance prediction: A systematic literature review (2015–2021),” International Journal of Emerging Technologies in Learning, vol. 17, no. 5, pp. 147–179, 2022. doi: 10.3991/ijet.v17i05.27685.

[3] C. Chaka, “Educational data mining, student academic performance prediction, prediction methods, algorithms and tools: An overview of reviews,” Journal of E-Learning and Knowledge Society, vol. 18, no. 2, pp. 58–69, 2022. doi: 10.20368/1971-8829/1135578.

[4] K. Alalawi, R. Athauda, and R. Chiong, “Contextualising the current state of research on the use of machine learning for student performance prediction: A systematic literature review,” Engineering Reports, vol. 5, no. 12, e12699, 2023. doi: 10.1002/eng2.12699.

[5] Y. S. Balcioğlu and M. Artar, “Predicting academic performance of students with machine learning,” Information Development, vol. 41, no. 3, 2025. doi: 10.1177/02666669231213023.

[6] M. D. Adane, J. K. Deku, and E. K. Asare, “Performance analysis of machine learning algorithms in prediction of student academic performance,” Journal of Advances in Mathematics and Computer Science, vol. 38, no. 5, pp. 74–86, 2023. doi: 10.9734/jamcs/2023/v38i51762.

[7] A. F. Meghji, F. B. Shaikh, S. A. Wadho, S. Bhatti, and R. K. Ayyasamy, “Using educational data mining to predict student academic performance,” VFAST Transactions on Software Engineering, vol. 11, no. 2, pp. 43–49, 2023. doi: 10.21015/vtse.v11i2.1475.

[8] P. Nayak, S. K. Vaheed, S. Gupta, and N. Mohan, “Predicting students’ academic performance by mining the educational data through machine learning-based classification model,” Education and Information Technologies, vol. 28, no. 11, pp. 14611–14637, 2023.

[9] S. Sengupta, “Towards finding a minimal set of features for predicting students’ performance using educational data mining,” International Journal of Modern Education and Computer Science, vol. 15, no. 3, pp. 44–54, 2023. doi: 10.5815/ijmecs.2023.03.04.

[10] X. Wang, Y. Zhao, C. Li, and P. Ren, “ProbSAP: A comprehensive and high-performance system for student academic performance prediction,” Pattern Recognition, vol. 137, article 109309, 2023. doi: 10.1016/j.patcog.2023.109309.

Share your valuable work from Social Media Buttons