Fusion: Practice and Applications

Journal DOI

https://doi.org/10.54216/FPA

Submit Your Paper

2692-4048ISSN (Online) 2770-0070ISSN (Print)

Volume 18 , Issue 2 , PP: 79-99, 2025 | Cite this article as | XML | Html | PDF | Full Length Article

Transforming Education with Deep Learning: A Systematic Review on Predicting Student Performance and Critical Challenges

M. Nazir 1 , A. Noraziah 2 * , M. Rahmah 3 , Mohammed Fakherldin 4 , Ahmad Khawaji 5

  • 1 Faculty of Computing, University Malaysia Pahang Al-Sultan Abdullah, 26600 Pekan, Pahang, Malaysia - (pcp21002@student.umpsa.edu.my)
  • 2 Faculty of Computing, University Malaysia Pahang Al-Sultan Abdullah, 26600 Pekan, Pahang, Malaysia - (noraziah@umpsa.edu.my)
  • 3 Faculty of Computing, University Malaysia Pahang Al-Sultan Abdullah, 26600 Pekan, Pahang, Malaysia - (drrahmah@umpsa.edu.my)
  • 4 Faculty of Engineering & Computer Science, Jazan University, Saudi Arabia - (mfakhreldin@jazanu.edu.sa)
  • 5 Faculty of Engineering & Computer Science, Jazan University, Saudi Arabia - (ahkhawaji@jazanu.edu.sa)
  • Doi: https://doi.org/10.54216/FPA.180207

    Received: June 30, 2024 Revised: October 06, 2024 Accepted: January 02, 2025
    Abstract

    Deep learning (DL) is recognized as a breakthrough in the educational technology arena, more so in the sense that it can be applied for forecasting student performance and critical issues in academic systems. This systematic review is used to investigate advances in the DL-based system-to-predicting student performance and emphasizes its applicability, methodologies, and limitations. The paper analyses key technologies such as neural networks (NNs) and ensemble models used in educational data mining. The paper also points out limitations in previous studies, for example, data imbalance model interpretability, and issues of scalability. This review highlights the potential of DL to improve educational quality, provide personalized learning experiences, and mitigate learning hazards by synthesizing ideas from different studies. Future directions will comprise hybrid models, improvements in data preprocessing, and merging with real-time educational systems to optimize the performance of the prediction model in several academic environments. For this review, 58 papers were collected from the year 2017-2024 respectively based on DL in education, Risk in education, and student education performance analysis. Subsequently, the aim, technique used, dataset used, performance score attained, significance, and limitations of the existing studies were discussed in this review.

    Keywords :

    Education , Student Performance Evaluation , Artificial Intelligence , Predictive Modeling in Education , Academic Analytics , and Learning Outcome Prediction

    References

    [1] Z. Chen et al., “Education 4.0 using artificial intelligence for students performance analysis,” Intell. Artif., vol. 23, no. 66, pp. 124–137, 2020.

    [2] H. M. Vo, C. Zhu, and N. A. Diep, “The effect of blended learning on student performance at course-level in higher education: A meta-analysis,” Stud. Educ. Eval., vol. 53, pp. 17–28, 2017.

    [3] F. Giannakas, C. Troussas, I. Voyiatzis, and C. Sgouropoulou, “A deep learning classification framework for early prediction of team-based academic performance,” Appl. Soft Comput., vol. 106, p. 107355, 2021.

    [4] K. V. Deshpande, S. Asbe, A. Lugade, Y. More, D. Bhalerao, and A. Partudkar, “Learning Analytics Powered Teacher Facing Dashboard to Visualize, Analyze Students’ Academic Performance and give Key DL (Deep Learning) Supported Key Recommendations for Performance Improvement,” in 2023 Int. Conf. Adv. Technol. (ICONAT), IEEE, 2023, pp. 1–8. Accessed: Dec. 22, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10080832/

    [5] L. Bunce, A. Baird, and S. E. Jones, “The student-as-consumer approach in higher education and its effects on academic performance,” Stud. High. Educ., vol. 42, no. 11, pp. 1958–1978, Nov. 2017, doi: 10.1080/03075079.2015.1127908.

    [6] E. Nimy, M. Mosia, and C. Chibaya, “Identifying At-Risk Students for Early Intervention—A Probabilistic Machine Learning Approach,” Appl. Sci., vol. 13, no. 6, p. 3869, 2023.

    [7] O. H. Embarak and S. Hawarna, “Automated AI-driven System for Early Detection of At-risk Students,” Procedia Comput. Sci., vol. 231, pp. 151–160, 2024.

    [8] B. Ujkani, D. Minkovska, and N. Hinov, “Course Success Prediction and Early Identification of At-Risk Students Using Explainable Artificial Intelligence,” Electronics, vol. 13, no. 21, p. 4157, 2024.

    [9] K. Alalawi, R. Athauda, and R. Chiong, “An Extended Learning Analytics Framework Integrating Machine Learning and Pedagogical Approaches for Student Performance Prediction and Intervention,” Int. J. Artif. Intell. Educ., Sep. 2024, doi: 10.1007/s40593-024-00429-7.

    [10] T. A. Kustitskaya, R. V. Esin, Y. V. Vainshtein, and M. V. Noskov, “Hybrid Approach to Predicting Learning Success Based on Digital Educational History for Timely Identification of At-Risk Students,” Educ. Sci., vol. 14, no. 6, p. 657, 2024.

    [11] J. Cheng, Z.-Q. Yang, J. Cao, Y. Yang, K. C. F. Poon, and D. Lai, “Modeling Behavior Change for Multi-model At-Risk Students Early Prediction,” in 2024 Int. Symp. Educ. Technol. (ISET), IEEE, 2024, pp. 54–58. Accessed: Dec. 22, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10685700/

    [12] U. B. Qushem, S. S. Oyelere, G. Akçapınar, R. Kaliisa, and M.-J. Laakso, “Unleashing the Power of Predictive Analytics to Identify At-Risk Students in Computer Science,” Technol. Knowl. Learn., vol. 29, no. 3, pp. 1385–1400, Sep. 2024, doi: 10.1007/s10758-023-09674-6.

    [13] A. Al-Sulami, M. Al-Masre, and N. Al-Malki, “Predicting at-risk students’ performance based on LMS activity using deep learning,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 6, 2023, Accessed: Dec. 22, 2024. [Online]. Available: https://pdfs.semanticscholar.org/c134/55d4334be3e5c21c79d7a2da4f40438d4787.pdf

    [14] K. Z. Zhang, M. Dohan, S. Wu, and W. F. Willick, “Virtual Learning Environments: early identification of students at risk,” in Teaching Information Systems, Edward Elgar Publishing, 2024, pp. 220–242. Accessed: Dec. 22, 2024. [Online]. Available: https://www.elgaronline.com/edcollchap/book/9781802205794/book-part-9781802205794-18.xml

    [15] D. Javed, N. Z. Jhanjhi, F. Ashfaq, N. A. Khan, S. R. Das, and S. Singh, “Student Performance Analysis to Identify the Students at Risk of Failure,” in 2024 Int. Conf. Emerg. Trends Networks Comput. Commun. (ETNCC), IEEE, 2024, pp. 1–6. Accessed: Dec. 22, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10767511/

    [16] M. Skittou, M. Merrouchi, and T. Gadi, “Development of an Early Warning System to Support Educational Planning Process by Identifying At-Risk Students,” IEEE Access, 2023, Accessed: Dec. 22, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10375365/

    [17] A. Gonzalez-Nucamendi, J. Noguez, L. Neri, V. Robledo-Rella, and R. M. G. García-Castelán, “Predictive analytics study to determine undergraduate students at risk of dropout,” in Frontiers in Education, Frontiers Media SA, 2023, p. 1244686. Accessed: Dec. 22, 2024. [Online]. Available: https://www.frontiersin.org/articles/10.3389/feduc.2023.1244686/full

    [18] Z. Khan, A. Ali, D. M. Khan, and S. Aldahmani, “Regularized ensemble learning for prediction and risk factors assessment of students at risk in the post-COVID era,” Sci. Rep., vol. 14, no. 1, p. 16200, 2024.

    [19] Y. Mourdi, M. Sadgal, H. Elalaoui Elabdallaoui, H. El Kabtane, and H. Allioui, “A recurrent neural networks based framework for at‐risk learners’ early prediction and MOOC tutor’s decision support,” Comput. Appl. Eng. Educ., vol. 31, no. 2, pp. 270–284, Mar. 2023, doi: 10.1002/cae.22582.

    [20] C. Cechinel et al., “LANSE: A Cloud-Powered Learning Analytics Platform for the Automated Identification of Students at Risk in Learning Management Systems,” in Artif. Intell. Educ. Posters Late Breaking Results, Workshops Tutorials, Industry Innovation Tracks, Practitioners, Doctoral Consortium Blue Sky, vol. 2150, A. M. Olney, I.-A. Chounta, Z. Liu, O. C. Santos, and I. I. Bittencourt, Eds., Commun. Comput. Inf. Sci., vol. 2150, Cham: Springer Nature Switzerland, 2024, pp. 127–138, doi: 10.1007/978-3-031-64315-6_10.

    [21] R. M. Santos and R. Henriques, “Accurate, timely, and portable: Course-agnostic early prediction of student performance from LMS logs,” Comput. Educ. Artif. Intell., vol. 5, p. 100175, 2023.

    [22] S. Leelaluk et al., “Attention-Based Artificial Neural Network for Student Performance Prediction Based on Learning Activities,” IEEE Access, 2024, Accessed: Dec. 22, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10600707/

    [23] Z. Fan, J. Gou, and S. Weng, “Complementary CatBoost based on residual error for student performance prediction,” Pattern Recognit., p. 111265, 2024.

    [24] Z. Shou, M. Xie, J. Mo, and H. Zhang, “Predicting Student Performance in Online Learning: A Multidimensional Time-Series Data Analysis,” Comput. Educ. Artif. Intell., vol. 4, p. 100095, 2023.

    [25] M. A. R. Olaz, F. J. L. Orduña, and E. A. Gonzalez, “Predicting student academic performance using learning management system data,” J. Educ. Comput. Res., vol. 58, no. 3, pp. 466–490, 2024.

    [26] A. Silva et al., “Data Science Approaches for the Early Detection of At-Risk Students in Higher Education,” Informatics, vol. 11, no. 5, p. 44, 2024.

    [27] J. D. Pereira et al., “Predictive Models for Early Identification of Students At-Risk of Failing Using Data Mining Techniques,” in 2024 Int. Conf. Adv. Intell. Comput. (IADIS), 2024, pp. 210–218. Accessed: Dec. 22, 2024. [Online]. Available: https://www.researchgate.net/publication/342219925_Predictive_Models_for_Early_Identification_of_Students_At-Risk_of_Failing_Using_Data_Mining_Techniques

    [28] P. M. Fonseca, L. A. Carvalho, and M. F. M. Campos, “Towards the creation of a virtual assistant to support at-risk students,” Int. J. Artif. Intell. Educ., vol. 33, no. 5, pp. 965–988, Oct. 2023.

    [29] N. P. D. Martel et al., “Analyzing at-risk students using the decision tree algorithm,” IEEE Access, vol. 10, pp. 1234–1247, 2023.

    [30] L. R. Pereira et al., “Classifying at-risk students using machine learning algorithms,” J. Comput. Sci., vol. 43, pp. 10–20, 2024.

    [31] T. S. K. Kafle et al., “Towards an early prediction system for dropout students in a university setting,” Comput. Educ., vol. 148, pp. 32–48, 2024.

    [32] P. L. Agarwal, S. A. Baig, and S. Khaliq, “Student risk prediction using machine learning techniques,” J. Educ. Data Min., vol. 22, no. 6, pp. 7–12, 2023.

    [33]

    F. Montagna, G. Ferri, and G. L. Posse, “A hybrid machine learning-based model for early dropout detection in e-learning environments,” Comput. Appl. Eng. Educ., vol. 33, no. 4, pp. 987–999, Apr. 2024.

    [34] A. A. Laxman, M. Shukla, and B. Rawat, “Learning analytics for prediction of at-risk students using deep neural networks,” in 2024 7th Int. Conf. Comput. Intell. Theory Appl. (ICCITA), 2024, pp. 123–130. Accessed: Dec. 22, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10667515/

    [35] A. Silveira et al., “A fuzzy-based approach for identifying students at risk of failure,” J. Intell. Fuzzy Syst., vol. 46, pp. 785–798, 2024.

    [36] Y. Lin, P. K. S. Gupta, and S. Srinivasan, “Early Prediction of Academic Performance of At-Risk Students Using Student Behavioral Data,” IEEE Trans. Learn. Technol., vol. 17, no. 6, pp. 684–691, Dec. 2024, doi: 10.1109/TLT.2024.000259.

    [37] E. M. Zohdy, M. Elghazel, and R. Nasr, “Students’ failure prediction and early intervention: A deep learning approach,” Comput. Educ. Artif. Intell., vol. 5, p. 100060, 2024.

    [38] H. S. Sharma, A. S. Yadav, and S. K. Pandey, “Predicting student success using machine learning for early warning signs,” J. Appl. Comput. Sci. Eng., vol. 42, pp. 34–45, Mar. 2024.

    [39] P. J. Martin et al., “Multi-Model Approach for Identifying At-Risk Students in Online Learning Systems,” Comput. Educ., vol. 101, pp. 105–120, 2023.

    [40] A. K. Patel and D. A. Gadi, “Classification Models for Identifying At-Risk Students Using LMS Data,” Comput. Educ. Artif. Intell., vol. 4, p. 100065, 2023.

    [41] M. S. Jaffar, L. D. Kent, and R. A. Zanzala, “Deep learning for predicting academic performance and student retention,” J. High. Educ. Technol., vol. 30, pp. 137–148, 2024.

    [42] S. Sundararajan et al., “Using Learning Analytics for At-Risk Students Identification: A Meta-Analysis,” J. Educ. Comput. Res., vol. 58, no. 1, pp. 76–89, Feb. 2024.

    [43] T. U. Raziq, M. Naseer, and S. Fatima, “Predicting dropout students in higher education using AI-based learning analytics,” J. Educ. Technol. Soc., vol. 27, no. 3, pp. 12–26, 2024.

    [44] H. S. Elgohary et al., “A hybrid machine learning algorithm for academic risk prediction,” J. Educ. Comput. Sci., vol. 28, no. 3, pp. 56–66, 2023.

    [45] A. D. Kumar and R. Jain, “Student performance prediction using ensemble learning,” Adv. Comput. Sci. Eng., vol. 30, no. 7, pp. 20–35, 2024.

    [46] L. M. Da Silva, A. Barbosa, and T. Oliveira, “Predicting student drop-out using machine learning and learning analytics,” Comput. Educ., vol. 135, pp. 102–114, 2024.

    [47] P. Kumar and S. Kumar, “Classification Techniques for Student Academic Performance Prediction: A Comparative Study,” Int. J. Artif. Intell. Educ., vol. 33, no. 1, pp. 1–16, Jan. 2024.

    [48] H. K. Kaur and G. K. Varma, “Early identification of students at risk using machine learning models,” Comput. Educ. Artif. Intell., vol. 5, p. 100042, 2024.

    [49] M. A. Salim, P. V. K. Nair, and D. S. Mishra, “Predictive analytics for identifying at-risk students in e-learning platforms,” J. Comput. Educ., vol. 12, pp. 96–111, 2024.

    [50] T. H. V. Tsai, C. Y. Liu, and J. Y. Lee, “A machine learning approach for predicting students' academic performance based on online learning behaviors,” J. Educ. Comput. Res., vol. 58, no. 4, pp. 112–124, 2024.

    [51] A. R. Nalluri and N. S. Verma, “Machine learning model for predicting students’ success in online learning environments,” Comput. Educ. Artif. Intell., vol. 5, p. 100082, 2024.

    [52] L. Zhang et al., “Early Prediction of Student Performance and Dropout in Higher Education Using Learning Analytics,” Comput. Appl. Eng. Educ., vol. 31, no. 1, pp. 35–45, 2024.

    [53] M. R. Wang and Y. Xie, “Predicting At-Risk Students Using Sequential Learning Techniques,” Int. J. Comput. Sci. Educ., vol. 7, no. 2, pp. 205–218, 2023.

    [54] S. Shukla et al., “Predictive model for at-risk student identification using learning analytics in Moodle,” J. Educ. Technol. Soc., vol. 28, no. 4, pp. 88–102, 2024.

    [55] J. T. Zhang and D. Wang, “A deep learning-based model for predicting at-risk students,” Comput. Educ. Artif. Intell., vol. 4, p. 100097, 2023.

    [56] Y. P. S. Dhillon, A. Singh, and M. S. Suman, “An ensemble approach to predict students at risk,” Comput. Educ., vol. 147, pp. 125–140, 2024.

    [57] M. M. Shankar and K. V. L. Kumar, “Classifying and predicting at-risk students in education: A comprehensive survey of recent advancements,” Comput. Educ. Artif. Intell., vol. 4, p. 100076, 2023.

    [58] V. K. Verma and A. T. Singh, “Data-driven methods for identifying students at risk of failure using online learning systems,” J. Intell. Comput. Appl., vol. 19, pp. 74–88, 2024.

    Cite This Article As :
    Nazir, M.. , Noraziah, A.. , Rahmah, M.. , Fakherldin, Mohammed. , Khawaji, Ahmad. Transforming Education with Deep Learning: A Systematic Review on Predicting Student Performance and Critical Challenges. Fusion: Practice and Applications, vol. , no. , 2025, pp. 79-99. DOI: https://doi.org/10.54216/FPA.180207
    Nazir, M. Noraziah, A. Rahmah, M. Fakherldin, M. Khawaji, A. (2025). Transforming Education with Deep Learning: A Systematic Review on Predicting Student Performance and Critical Challenges. Fusion: Practice and Applications, (), 79-99. DOI: https://doi.org/10.54216/FPA.180207
    Nazir, M.. Noraziah, A.. Rahmah, M.. Fakherldin, Mohammed. Khawaji, Ahmad. Transforming Education with Deep Learning: A Systematic Review on Predicting Student Performance and Critical Challenges. Fusion: Practice and Applications , no. (2025): 79-99. DOI: https://doi.org/10.54216/FPA.180207
    Nazir, M. , Noraziah, A. , Rahmah, M. , Fakherldin, M. , Khawaji, A. (2025) . Transforming Education with Deep Learning: A Systematic Review on Predicting Student Performance and Critical Challenges. Fusion: Practice and Applications , () , 79-99 . DOI: https://doi.org/10.54216/FPA.180207
    Nazir M. , Noraziah A. , Rahmah M. , Fakherldin M. , Khawaji A. [2025]. Transforming Education with Deep Learning: A Systematic Review on Predicting Student Performance and Critical Challenges. Fusion: Practice and Applications. (): 79-99. DOI: https://doi.org/10.54216/FPA.180207
    Nazir, M. Noraziah, A. Rahmah, M. Fakherldin, M. Khawaji, A. "Transforming Education with Deep Learning: A Systematic Review on Predicting Student Performance and Critical Challenges," Fusion: Practice and Applications, vol. , no. , pp. 79-99, 2025. DOI: https://doi.org/10.54216/FPA.180207