Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1363
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-14T22:01:52.971003Z
status: published
lens: g_space
sector: education
headline: Design and Evaluation of an Artificial Intelligence–Based Model for Predicting Twelfth-Grade Students’ Mathematics Performance Based on Individual, Educational, and Learning Technology Factors
dek: 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 in…
gain_title: A gradient boosting model combining prior achievement, psychological, instructional and learning-technology factors predicted twelfth-grade math scores with acceptable accuracy.
problem_title: (none)
trace_subject: (none)
gain_reading: A gradient boosting model combining prior achievement, psychological, instructional and learning-technology factors predicted twelfth-grade math scores with acceptable accuracy.
gain_evidence: gradient boosting regression achieved the best predictive performance | mathematics performance can be predicted with acceptable accuracy
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers compared eight regression and machine-learning algorithms on questionnaire and score data from twelfth-grade experimental sciences students in Isfahan, Iran. Gradient boosting regression performed best on the held-out test set, with a mean absolute error of 0.93 and a coefficient of determination of .72.

The result suggests that school-level data on prior achievement, motivation, teaching and technology use could help flag likely math performance. However, the model was built on a small retained sample from one city and was validated only internally, so how well it transfers elsewhere is unknown.
limitation: The final analysis rests on only 84 students from one city's twelfth-grade experimental sciences cohort, and validation was internal, which limits how far the findings generalize.
tag: Evidence-backed gain
key_points: Of 187 questionnaires distributed, only 84 student records were retained for analysis after removing incomplete, inconsistent, and invalid ones. | Previous math achievement correlated most strongly with current performance, followed by self-efficacy, study regularity, motivation, teacher feedback, instructional quality and educational technology use. | Test anxiety and digital distraction were negatively associated with math performance. | Explained variance rose from .54 to .65 with educational factors and to .72 once learning technology factors were added.
rundown: The study was applied, quantitative, cross-sectional and predictive. It used a structured questionnaire covering individual factors, educational conditions and learning technology variables, paired with students' recorded math scores.

Multiple linear, ridge, lasso, elastic net, decision tree, random forest, gradient boosting and support vector regression were compared using mean absolute error, root mean squared error and the coefficient of determination. Repeated five-fold cross-validation was used for internal model development after a train/test split.

The most influential predictors were prior math achievement, self-efficacy, study regularity, teacher feedback, educational use of learning technologies, test anxiety and instructional quality. The authors describe the model as interpretable.
sources:
- peer_reviewed | International Journal of Education and Cognitive Sciences | https://journalecs.com/index.php/ecs/article/view/428 | 2026-11-01
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

2dfc8018ebdeeb5310baabecb31c38fed80b8741e8c92677c87fc9709dc23466

previous

0000000000000000000000000000000000000000000000000000000000000000