NAWOA-XGBoost: A Novel Model for Early Prediction of Academic Potential in Computer Science Students

TL;DR

This paper introduces NAWOA, an improved whale optimization algorithm, and applies it to develop NAWOA-XGBoost for early prediction of academic potential in computer science students, showing superior performance over traditional methods.

Contribution

The study proposes a novel nonlinear adaptive whale optimization algorithm and demonstrates its effectiveness in hyperparameter tuning for academic potential prediction models.

Findings

NAWOA outperforms standard WOA in benchmark tests.

NAWOA-XGBoost achieves higher accuracy and AUC than traditional models.

Model shows strong adaptability on imbalanced datasets.

Abstract

Whale Optimization Algorithm (WOA) suffers from limited global search ability, slow convergence, and tendency to fall into local optima, restricting its effectiveness in hyperparameter optimization for machine learning models. To address these issues, this study proposes a Nonlinear Adaptive Whale Optimization Algorithm (NAWOA), which integrates strategies such as Good Nodes Set initialization, Leader-Followers Foraging, Dynamic Encircling Prey, Triangular Hunting, and a nonlinear convergence factor to enhance exploration, exploitation, and convergence stability. Experiments on 23 benchmark functions demonstrate NAWOA's superior optimization capability and robustness. Based on this optimizer, an NAWOA-XGBoost model was developed to predict academic potential using data from 495 Computer Science undergraduates at Macao Polytechnic University (2009-2019). Results show that NAWOA-XGBoost outperforms traditional XGBoost and WOA-XGBoost across key metrics, including Accuracy (0.8148), Macro F1 (0.8101), AUC (0.8932), and G-Mean (0.8172), demonstrating strong adaptability on multi-class imbalanced datasets.