Design and Evaluation of an Artificial Intelligence–Based Model for Predicting Twelfth-Grade Students’ Mathematics Performance Based on Individual, Educational, and Learning Technology Factors

Najmeh  Yosefi; Mahdi Azhini; Hamidreza  Kashefi; Nourooz  Hashemi

Authors

Najmeh Yosefi Department of Mathematics, SR.C., Islamic Azad University, Tehran, Iran Author https://orcid.org/0009-0004-2715-0313
Mahdi Azhini Department of Mathematics, SR.C., Islamic Azad University, Tehran, Iran https://orcid.org/0000-0001-6390-0266
Hamidreza Kashefi Department of Mathematics Education, Farhangian University, Tehran, Iran Author https://orcid.org/0000-0001-5463-4453
Nourooz Hashemi Department of Mathematics Education, Farhangian University, Tehran, Iran Author https://orcid.org/0000-0002-9180-8958

Keywords:

Artificial intelligence, machine learning, mathematics performance, predictive modeling, twelfth-grade students, educational technology, self-efficacy, gradient boosting

Abstract

Purpose: This study aimed to design and evaluate an artificial intelligence–based model for predicting the mathematics performance of twelfth-grade experimental sciences students based on individual, educational, and learning technology factors.

Methods and Materials: This applied, quantitative, cross-sectional, and predictive study was conducted among twelfth-grade experimental sciences students in Isfahan, Iran. A total of 187 questionnaires were distributed, and after removing incomplete, inconsistent, and invalid records, data from 84 students were retained for analysis. Data were collected using a structured questionnaire assessing individual factors, educational conditions, and learning technology variables, together with students’ recorded mathematics scores. The dataset was divided into training and testing subsets, and repeated five-fold cross-validation was used for internal model development. Multiple linear regression, ridge regression, lasso regression, elastic net regression, decision tree regression, random forest regression, gradient boosting regression, and support vector regression were compared. Model performance was evaluated using mean absolute error, root mean squared error, and the coefficient of determination.

Findings: Previous mathematics achievement had the strongest positive correlation with current mathematics performance, followed by mathematics self-efficacy, study regularity, academic motivation, teacher feedback, instructional quality, and educational use of learning technologies. Test anxiety and digital distraction were negatively associated with mathematics performance. Among the evaluated algorithms, gradient boosting regression achieved the best predictive performance, with a test-set mean absolute error of 0.93, root mean squared error of 1.26, and coefficient of determination of .72. Previous mathematics achievement, mathematics self-efficacy, study regularity, teacher feedback, educational use of learning technologies, test anxiety, and instructional quality were the most influential predictors. Adding educational factors increased explained variance from .54 to .65, while including learning technology factors further increased it to .72.

Conclusion: The findings indicate that mathematics performance can be predicted with acceptable accuracy by integrating students’ prior achievement, psychological and behavioral characteristics, instructional experiences, and learning technology use within an interpretable artificial intelligence model.

Downloads

Download data is not yet available.

References

Akpan, E. T., Umoh, J. B., & James, G. D. (2024). Principal Component Analysis of Cognitive Executive Functions: A Predictive Model of Academic Performance of Students in Mathematics in Secondary Schools. Asian Journal of Education and Social Studies, 50(6), 222-231. https://doi.org/10.9734/ajess/2024/v50i61408

Allahkarami, A. (2025). The effect of Wordwall artificial intelligence on students' agentic engagement and academic performance in mathematics. Technology and Scholarship in Education, 5(Special Issue, Autumn). https://doi.org/10.30473/t-edu.2025.75854.1332

Arefi, M. (2024). Examining the Effect of Active Teaching Methods, Such as Games and Projects, on Students' Motivation and Academic Performance in Mathematics. First International Conference on Transformative Ideas in Cultural and Educational Studies in Education with Emphasis on Action Research, Lesson Study, and Narrative Research in the Third Millennium,

Awofala, A. O. A., Akinoso, S. O., Adeniyi, C. O., Jega, S. H., Fatade, A. O., & Arigbabu, A. A. (2024). Primary teachers' mathematics anxiety and mathematics teaching anxiety as predictors of students' performance in mathematics. ASEAN Journal of Science and Engineering Education, 4(1), 9–24. https://doi.org/10.17509/ajsee.v3i3.51065

Catador, J. A. (2024). Examining the Correlation and Predictive Power of Metacognitive Domains on Mathematics Performance Among Senior High School Students. Jip, 2(7). https://doi.org/10.69569/jip.2024.0192

Chen, S. (2024). Innovative Work Behavior and Job Performance of Corporate Employees in the Age of Artificial Intelligence. Applied Mathematics and Nonlinear Sciences, 9(1). https://doi.org/10.2478/amns-2024-0856

Dano, M., & Prado, N. (2024). Innovative Curriculum Design, Classroom Management Strategies, Competencies, and Mathematics Teachers' Performance: A Causal Model. Psychology and Education: A Multidisciplinary Journal, 27(2), 199-203. https://scimatic.org/

Galamiton, E. (2025). Self-Efficacy and Peer Support on Alternative Learning System Learners' Performance In Mathematics. Pemj, 35(8), 916-921. https://doi.org/10.70838/pemj.350806

Gomez-Talal, I., Bote-Curiel, L., & Rojo-Alvarez, J. L. (2024). Understanding the Disparities in Mathematics Performance: An Interpretability-Based Examination. Engineering Applications of Artificial Intelligence, 133(Part B), 108109. https://doi.org/10.1016/j.engappai.2024.108109

Li, Z. (2025). Using Deep Learning Techniques to Study the Effects of Psychological Stress on College Students’ Performance in Physical Education Classes. Applied Mathematics and Nonlinear Sciences, 10(1). https://doi.org/10.2478/amns-2025-0549

Niu, J., Xu, H., & Yu, J. (2025). Identifying multilevel factors on student mathematics performance. Palgrave Communications, 12, 151. https://doi.org/10.1057/s41599-025-04466-y

Ocampo, E. N., Mobo, F. D., & Cutillas, A. L. (2023). Exploring the Relationship between Mathematics Performance and Learning Style among Grade 8 Students. International Journal of Multidisciplinary: Applied Business and Education Research, 4(4), 1165–1172. https://doi.org/10.11594/ijmaber.04.04.14

Oh, S. (2024). Exploring Gifted School Students’ Process-Based Assessment Performance Using GeoGebra: Focused on the Quadratic Curves. Kor SCH Mathematics Soc, 27(2), 241-255. https://doi.org/10.30807/ksms.2024.27.2.007

Omale, O. (2024). Innovating Assessment Through the use of Tailored Testing on Student Achievement of Senior Secondary Mathematics Students in Kogi State. International Journal of Education and Cognitive Sciences, 5(3), 1-7. https://doi.org/10.61838/kman.ijeas.5.3.1

Psyridou, M., Koponen, T., Tolvanen, A., Aunola, K., Lerkkanen, M.-K., Poikkeus, A.-M., & Torppa, M. (2024). Early prediction of math difficulties with the use of a neural networks model. Journal of Educational Psychology, 116(2), 212-232. https://doi.org/10.1037/edu0000835

Samavati, M., Pourrostai Ardakani, S., Jameh Bozorg, Z., Zarei Zavarki, E., & Aliabadi, K. (2024). The impact of adaptive game-based learning on mathematics performance of students with learning disabilities in a mobile learning environment. Quarterly Journal of Psychological Sciences, 23(135), 503–522. https://psychologicalscience.ir/article-1-2158-fa.html

Shaheema, A., Azar, A. S., & Ahmad, A. (2023). The Key Connection Between the Elements of Self-Regulated Learning (SRL) and Mathematics Performance: Literature Review. Education Quarterly Reviews, 6(3). https://doi.org/10.31014/aior.1993.06.03.770

Tepho, S., & Srisawasdi, N. (2023). Assessing Impact of Tablet-Based Digital Games on Mathematics Learning Performance. Engineering Proceedings, 38(1), 41. https://doi.org/10.3390/engproc2023038041

Uwineza, I., Uworwabayeho, A., & Yokoyama, K. (2023). Effects of Interactive Mathematics Software on Grade-5 Learners’ Performance. International Journal of Learning Teaching and Educational Research, 22(1), 166-190. https://doi.org/10.26803/ijlter.22.1.10

Wang, X., Houang, R. T., Schmidt, W. H., & Kelly, K. S. (2024). Relationship Between Opportunity to Learn, Mathematics Self-Efficacy, and Math Performance: Evidence from PISA 2012 in 63 Countries and Economies. International Journal of Science and Mathematics Education, 1-26. https://doi.org/10.1007/s10763-024-10446-6

Wijaya, T. T., Yu, B., Xu, F., Yuan, Z., & Mailizar, M. (2023). Analysis of factors affecting academic performance of mathematics education doctoral students: a structural equation modeling approach. Int. J. Environ. Res. Public Health, 20, 4518. https://doi.org/10.3390/ijerph20054518

Wong, Z. Y., Liem, G. A. D., Chan, M., & Datu, J. A. D. (2024). Student engagement and its association with mathematics performance and subjective well-being: A systematic review and meta-analysis. Journal of Educational Psychology, 116(1), 48-75. https://doi.org/10.1037/edu0000833

Yalçın, M., & Erdoğan, M. (2023). Analyzing the effect of teacher feedback on student performance in mathematics. Journal of Mathematics Education, 15(3), 200-215.

Yarkwah, C., Kpotosu, C. K., & Gbormittah, D. (2024). Effect of Test Anxiety on Students' Academic Performance in Mathematics at the Senior High School Level. Discover Education, 3(1), 245. https://doi.org/10.1007/s44217-024-00343-z

Zhu, L., You, H., Minju, & Fang, F. (2025). Predictive Insights into U.S. Students' Mathematics Performance on PISA 2022 Using Ensemble Tree-Based Machine Learning Models. International Journal of Educational Research, 130(5), 102537. https://doi.org/10.1016/j.ijer.2025.102537