Skip to main content

Causal Discovery and Features Importance Analysis: What Can Be Inferred About At-Risk Students?

  • Conference paper
  • First Online:
Business Intelligence (CBI 2023)

Abstract

In this paper, we introduced machine learning and causal discovery algorithms that can be used as a way to determine the relevant characters of students with low performances issues and to analyze their implications to highlight this type of students. Through this, we aim to provide some new useful insights that can allow to predict and explain the inherent relationships. By using six machine learning algorithms (Gradient Boosting, K-nearest neighbors, SVM, Random Forest, and Decision Tree) and four causal discovery algorithms (PC, GES, LinGAM, and GOLEM), we try to develop and use these models to analyze and draw conclusions from patterns and data. In this study, we present these algorithms to show the performance of the developed models in explaining the effect of variables and the nature of their relationship with low performing students. The results revealed that these models produce useful insights and highlight the existing relationship among students with low performances in reading and other student characters.

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

Access this chapter

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

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Glymour, C., Zhang, K., Spirtes, P.: Review of causal discovery methods based on graphical models. Front. Genet. 10, 524 (2019). https://doi.org/10.3389/fgene.2019.00524

    Article  Google Scholar 

  2. Quintana, R.: The structure of academic achievement: searching for proximal mechanisms using causal discovery algorithms. Sociol. Methods Res. 52(1), 85ā€“134 (2023). https://doi.org/10.1177/0049124120926208

    Article  MathSciNet  Google Scholar 

  3. Chen, H., Du, K., Yang, X., Li, C.: A review and roadmap of deep learning causal discovery in different variable paradigms. ArXiv abs/2209.06367 (2022)

    Google Scholar 

  4. Schƶlkopf, B., von KĆ¼gelgen, J.: From statistical to causal learning. arXiv preprint arXiv:2204.00607 (2022)

  5. Upadhyaya, P., Zhang, K., Li, C., Jiang, X., Kim, Y.: Scalable causal structure learning: scoping review of traditional and deep learning algorithms and new opportunities in biomedicine. JMIR Med. Inform. (2023). https://doi.org/10.2196/38266

    Article  Google Scholar 

  6. Fancsali, S.: Causal discovery with models: behavior, affect, and learning in cognitive tutor Algebra (2014)

    Google Scholar 

  7. Yong D., Fan, L., Liu, X.: Analysis of feature matrix in machine learning algorithms to predict energy consumption of public buildings. Energy Build. 249, 111208 (2022). https://doi.org/10.1016/j.enbuild.2021.111208

  8. OCDE : Low-performing students: why they fall behind and how to help them succeed, PISA, Ɖditions OCDE, Paris (2016). https://doi.org/10.1787/9789264250246-en

  9. Ibourk, A., Hnini, K., Ouaadi, I.: Analysis of the pedagogical effectiveness of teacher qualification cycle in Morocco: a machine learning model approach. In: Kacprzyk, J., Ezziyyani, M., Balas, V.E. (eds.) International Conference on Advanced Intelligent Systems for Sustainable Development. AI2SD 2022. Lecture Notes in Networks and Systems, vol. 637. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-26384-2_30

  10. Ibourk, A., Ouaadi, I.: An exploration of student grade retention prediction using machine learning algorithms. In: Fakir, M., Baslam, M., El Ayachi, R. (eds.) Business Intelligence. CBI 2022. Lecture Notes in Business Information Processing, vol. 449, pp. 94ā€“106. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-06458-6_8

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ismail Ouaadi .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

Ā© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ouaadi, I., Ibourk, A. (2023). Causal Discovery and Features Importance Analysis: What Can Be Inferred About At-Risk Students?. In: El Ayachi, R., Fakir, M., Baslam, M. (eds) Business Intelligence. CBI 2023. Lecture Notes in Business Information Processing, vol 484 . Springer, Cham. https://doi.org/10.1007/978-3-031-37872-0_10

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-37872-0_10

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-37871-3

  • Online ISBN: 978-3-031-37872-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics