A New Method Based on Belief Rule Base with Balanced Accuracy and Interpretability for Student Achievement Prediction

Zongjun Zhang, Qian Deng, Wei He () and Cuiping Yang ()
Additional contact information
Zongjun Zhang: School of Computer Science and Information Engineering, Harbin Normal University, Harbin 150025, China
Qian Deng: School of Computer Science and Information Engineering, Harbin Normal University, Harbin 150025, China
Wei He: School of Computer Science and Information Engineering, Harbin Normal University, Harbin 150025, China
Cuiping Yang: School of Computer Science and Information Engineering, Harbin Normal University, Harbin 150025, China

Mathematics, 2024, vol. 12, issue 20, 1-21

Abstract: In the field of education, the accurate prediction of students’ future performance is essential for personalized instruction and efficient allocation of resources. Such predictions not only help education professionals develop targeted educational strategies but also identify students’ learning needs at an early stage so that timely interventions and support can be provided. To gain the trust of educational experts and ensure the practical application value of the prediction results, the prediction methods used must be highly interpretable. However, there are two problems with the current belief rule base (BRB) applied to student performance prediction. First, there is a current lack of effective strategies for enhancing the interpretability of the optimization process. Second, BRB models that overemphasize accuracy tend to exhibit characteristics of black-box models. To overcome these challenges, this paper proposes a new method based on BRB with balanced accuracy and interpretability (BRB-Bai) for student achievement prediction. First, an attribute selection method is proposed to filter out important features associated with student performance. Then, expert knowledge credibility is calculated, and four interpretability strategies are proposed to ensure the interpretability of the model and to achieve a balance between interpretability and accuracy on the basis of expert knowledge credibility. The effectiveness of the proposed model is demonstrated by conducting experiments on the student achievement dataset.

Keywords: student achievement prediction; belief rule base; expert knowledge credibility; accuracy; interpretability (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/20/3283/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/20/3283/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:20:p:3283-:d:1502469

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().