A Hybrid Al-Biruni Earth Radius–Stochastic Fractal Search

Optimized XGBoost Model for Accurate Student Performance

Prediction

Abdelaziz A. Abdelhamid1,* Amal H. Alharbi2

1 Department of Computer Science, Faculty of Computer and Information Sciences, Ain Shams University, Cairo 11566, Egypt

2 Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University,

P.O. Box 84428, Riyadh 11671, Saudi Arabia

Received: December 09, 2025 Revised: February 10, 2026 Accepted: April 14, 2026 ⋆ Corresponding author

ABSTRACT

The ability to accurately predict student academic performance is now an established pillar of contemporary

educational data mining, driven by the desire for data-driven interventions and personalized learning. This paper

presents a mixed-methodology optimization and machine learning model that combines the Al-Biruni Earth Radius-

Stochastic Fractal Search (BER-SFS) algorithm with eXtreme Gradient Boosting (XGBoost) to improve predictive

accuracy and model stability in forecasting student performance. The proposed BER-SFS + XGBoost model

is an optimized system that systematically optimises the hyperparameter based on dual exploration-exploitation

mechanism to reduce the Mean Squared Error (MSE) of the baseline XGBoost model of 0.0226 to 0.00029 and

the Root Mean Squared Error (RMSE) of the baseline XGBoost model to 0.1504 to 0.00194 and the coefficient of

determination R2 of 0.9019 to Comparison to the other metaheuristics, including theGrey Wolf Optimizer (GWO),

Particle Swarm Optimization (PSO) and Whale Optimization Algorithm (WOA) proved the superiority of the

suggested hybrid model in all metrics of the evaluation. These findings support the potential to combine the dynamics

of geometric exploration provided by BER with those of diffusion-based refinement offered by SFS to achieve high

generalization and minimal bias. The implications extend beyond predictive analytics, demonstrating that the hybrid

metaheuristic optimization approach can serve as a scalable, explainable method for adaptive educational systems,

enabling early detection of at-risk learners and the development of data-driven academic support mechanisms.

Keywords: Educational Data Mining (EDM) Hybrid Metaheuristic Optimization Al-Biruni Earth Radius–Stochastic

Fractal Search (BER–SFS) eXtreme Gradient Boosting (XGBoost) Student Performance Prediction.

1. INTRODUCTION

One of the most significant areas of contemporary educational

research is students’ academic performance. On other

tiers, schools also face the challenge of ensuring that student

performance is treated holistically rather than limited

to grades or test scores [1]. Student performance measurement

is not merely a combination of independent variables,

including cognitive outcomes, student engagement and motivation,

socio-economic status, and school support systems.

Such variables are generally dynamic and create patterns that

cannot be easily analysed using conventional methods. As

described in the study by [2], student performance does not

depend solely on academic ability but also on personal, environmental,

and institutional factors that influence learning