Author Information
Iyad Suleiman, Tel Hai Academic College, IsraelRozan Abbas, The Max Stern Yezreel Valley College, Israel
Amani Attallah, The Max Stern Yezreel Valley College, Israel
Rula Jiryis, Kinneret Academic College, Israel
Abstract
Mathematics achievement is widely recognized as a critical predictor of academic success and future participation in science, technology, engineering, and mathematics (STEM) fields. However, many educational systems struggle to identify students at risk of underperformance early enough to provide effective intervention. This study proposes a data-driven approach for predicting a new student’s mathematics achievement based on historical student performance data. Using a publicly available dataset, two predictive modeling techniques—multiple linear regression and random forest regression (see Breiman, 2001; Kuhn & Johnson, 2013)—are applied to estimate mathematics scores and identify key contributing factors. The modeling pipeline includes data preprocessing, categorical encoding, feature scaling, feature selection, and cross-validation. Model performance is evaluated using mean squared error (MSE) and the coefficient of determination (R²). Results indicate that multiple linear regression outperforms random forest regression in both predictive accuracy and interpretability, with reading and writing scores emerging as the most influential predictors. The findings highlight the potential of interpretable machine learning models to support educational decision-making and targeted pedagogical interventions (Breiman, 2001; OECD, 2019; Siegler et al., 2012).
Paper Information
Conference: IICE2026Stream: Learning Experiences
This paper is part of the IICE2026 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window
To cite this article:
Suleiman I., Abbas R., Attallah A., & Jiryis R. (2026) Predicting a New Student’s Mathematics Achievement Based on Prior Student Performance ISSN: 2189-1036 – The IAFOR International Conference on Education – Hawaii 2026 Official Conference Proceedings (pp. 1-8) https://doi.org/10.22492/issn.2189-1036.2026.1
To link to this article: https://doi.org/10.22492/issn.2189-1036.2026.1
Comments
Powered by WP LinkPress