Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

XAI-Based Student Performance Prediction: Peeling Back the Layers of LSTM and Random Forest’s Black Boxes

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

This paper focuses on enhancing the accuracy of student performance prediction using LSTM and Random Forest algorithms. These algorithms are trained on Jordan datasets and also aimed to shed light on their internal workings. The methods of LIME and SHAP for achieving explainability have been employed to gain insights into the inner mechanisms of these prediction models. The study found that different explanation techniques yielded diverse outcomes in identifying the crucial factors influencing student success, even when using the same group of students and machine learning models. The results revealed that the LSTM model was predominantly influenced by the Parent Answering Survey and behavior features, as revealed by the LIME and SHAP methodologies. Conversely, the SPAP and LIME techniques unveiled that the Students Absence Days and Behavior features had a more pronounced influence on explaining the outcomes of the RF model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Data Availability

The dataset generated and analyzed during the current study are available from the corresponding author on reasonable request.

References

  1. Adnan M, Habib A, Ashraf J, Mussadiq S, Raza AA, Abid M, Bashir M, Khan SU. Predicting at-risk students at different percentages of course length for early intervention using machine learning models. Ieee Access. 2021;5(9):7519–39.

    Article  Google Scholar 

  2. Alwarthan S, Aslam N, Khan IU. An explainable model for identifying at-risk student at higher education. IEEE Access. 2022;30(10):107649–68.

    Article  Google Scholar 

  3. Alyahyan E, Düşteaör D. Decision Trees for Very Early Prediction of Student's Achievement. In2020 2nd International Conference on Computer and Information Sciences (ICCIS) 2020 Oct 13 pp. 1–7. IEEE

  4. Baashar Y, Alkawsi G, Mustafa A, Alkahtani AA, Alsariera YA, Ali AQ, Hashim W, Tiong SK. Toward predicting student’s academic performance using artificial neural networks (ANNs). Appl Sci. 2022;12(3):1289.

    Article  Google Scholar 

  5. Baranyi M, Nagy M, Molontay R. Interpretable deep learning for university dropout prediction. InProceedings of the 21st annual conference on information technology education 2020 Oct 7 (pp. 13–19)

  6. Burkart N, Huber MF. A survey on the explainability of supervised machine learning. J Artif Intell Res. 2021;19(70):245–317.

    Article  MathSciNet  MATH  Google Scholar 

  7. Coussement K, Phan M, De Caigny A, Benoit DF, Raes A. Predicting student dropout in subscription-based online learning environments: the beneficial impact of the logit leaf model. Decis Support Syst. 2020;1(135): 113325.

    Article  Google Scholar 

  8. Chen Fu, Cui Y. Utilizing student time series behaviour in learning management systems for early prediction of course performance. J Learn Anal. 2020;7(2):1–17.

    Article  Google Scholar 

  9. Eason G, Noble B, Sneddon IN. On certain integrals of Lipschitz-Hankel type involving products of Bessel functions. Phil Trans Roy Soc London. 1955;A247:529–51.

    MathSciNet  MATH  Google Scholar 

  10. Ferreira A, Madeira SC, Gromicho M, de Carvalho M, Vinga S, Carvalho AM. Predictive medicine using interpretable recurrent neural networks. In: Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10–15, 2021. Lecture Notes in Computer Science book series (LNIP, Vol. 12661), Proceedings, Part I 2021 Feb 21. Cham: Springer International Publishing; 2021. p. 187–202

  11. Hasib KM, Rahman F, Hasnat R, Alam MG. A machine learning and explainable ai approach for predicting secondary school student performance. In2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC) 2022 Jan 26 (pp. 0399–0405). IEEE

  12. Injadat M, Moubayed A, Nassif AB, Shami A. Multi-split optimized bagging ensemble model selection for multi-class educational data mining. Appl Intell. 2020;50:4506–28.

    Article  Google Scholar 

  13. Khosravi H, Shum SB, Chen G, Conati C, Tsai YS, Kay J, Knight S, Martinez-Maldonado R, Sadiq S, Gaševi’c D. Explainable artificial intelligence in education. Comput Educ Artif Intell. 2022;3: 100074.

    Article  Google Scholar 

  14. Klaise J, Van Looveren A, Vacanti G, Coca A. Alibi explain: Algorithms for explaining machine learning models. J Mach Learn Res. 2021;22(1):8194–200.

    MATH  Google Scholar 

  15. Marras M, Julien Tuang Tu Vignoud, and Tanja Kaser. Can feature predictive power generalize? benchmarking early predictors of student success across piped and online courses. In 14th International Conference on Educational Data Mining, pages. 2021;150:160

  16. S. Mazzanti, "Shap values explained exactly how you wished someone explained to you," https://towardsdatascience.com/shap-explained-the-wayi-wish-someone-explained-it-to-me-ab81cc69ef30. Accessed 4 Jan 2020

  17. Molnar C. Interpretable Machine Learning. 2nd edition, 2022

  18. Pei B, Xing W. An interpretable pipeline for identifying at-risk students. J Educ Comput Res. 2022;60(2):380–405.

    Article  Google Scholar 

  19. Piscitello J, Kim YK, Orooji M, Robison S. Sociodemographic risk, school engagement, and community characteristics: a mediated approach to understanding high school dropout. Child Youth Serv Rev. 2022;133: 106347.

    Article  Google Scholar 

  20. Ramaswami G, Susnjak T, Mathrani A, Lim J, Garcia P. Using educational data mining techniques to increase the prediction accuracy of student academic performance. Inf Learn Sci. 2019;120(7/8):451–67.

    Article  Google Scholar 

  21. Scheers H, De Laet T. Interactive and explainable advising dashboard opens the black box of student success prediction. InTechnology-Enhanced Learning for a Free, Safe, and Sustainable World: 16th European Conference on Technology Enhanced Learning, EC-TEL 2021, Bolzano, Italy, September 20–24, 2021, Proceedings 16 2021 (pp. 52–66). Springer International Publishing

  22. Veerasamy AK, D'Souza D, Apiola MV, Laakso MJ, Salakoski T. Using early assessment performance as early warning signs to identify at-risk students in programming courses. In2020 IEEE Frontiers in Education Conference (FIE) 2020 Oct 21 pp. 1–9. IEEE

  23. Vultureanu-Albi si A, and Costin B adic a. Improving students' performance by interpretable explanations using ensemble tree-based approaches. In IEEE 15th International Symposium on Applied Computational Intelligence and Informatics, pages 215{220. IEEE, 2021

  24. Yağcı M. Educational data mining: prediction of students’ academic performance using machine learning algorithms. Smart Learn Environ. 2022;9(1):11.

    Article  Google Scholar 

Download references

Funding

No funding was received for this research.

Author information

Authors and Affiliations

  1. Department of Computer Science, Presidency University, Bangalore, 560025, India

    N. Kartik

  2. Department of Computer Application, Presidency College, Bangalore, 560024, India

    N. Kartik & R. Mahalakshmi

  3. School of Mathematics and Natural Science, Chanakya University, Bangalore, 562110, India

    K. A. Venkatesh

Authors
  1. N. Kartik
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. R. Mahalakshmi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. K. A. Venkatesh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to N. Kartik.

Ethics declarations

Conflict of Interest

No conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the topical collection “Advances in Computational Approaches for Image Processing, Wireless Networks, Cloud Applications and Network Security” guest edited by P. Raviraj, Maode Ma and Roopashree H R.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kartik, N., Mahalakshmi, R. & Venkatesh, K.A. XAI-Based Student Performance Prediction: Peeling Back the Layers of LSTM and Random Forest’s Black Boxes. SN COMPUT. SCI. 4, 699 (2023). https://doi.org/10.1007/s42979-023-02070-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-023-02070-y

Keywords

Search

Navigation