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

2025-12-04

AI Summary

To address the premature convergence and slow convergence issues of the Whale Optimization Algorithm (WOA) in XGBoost hyperparameter optimization, this paper proposes a Nonlinear Adaptive Whale Optimization Algorithm (NAWOA). NAWOA integrates five key enhancements: Good Nodes Set-based initialization, a Leader-Followers Foraging mechanism, a dynamic prey-encircling strategy, a triangular cooperative hunting structure, and a nonlinear convergence factor—collectively strengthening global exploration and convergence stability. We embed NAWOA into XGBoost hyperparameter tuning to construct the NAWOA-XGBoost model, applied to early academic potential prediction for students—a multiclass, class-imbalanced educational task. Evaluated on a real-world dataset of 495 students, the model achieves accuracy = 0.8148, macro-F1 = 0.8101, AUC = 0.8932, and G-mean = 0.8172, consistently outperforming standard XGBoost and WOA-XGBoost. Results validate both the effectiveness and practical applicability of the proposed algorithmic improvements.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Ensemble Methods
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Enhances Whale Optimization Algorithm's global search and convergence
• Optimizes XGBoost hyperparameters for academic potential prediction
• Addresses multi-class imbalanced datasets in student performance forecasting

Innovation

• Enhanced WOA with nonlinear adaptive strategies for optimization
• Integrated Good Nodes Set and dynamic foraging for stability
• Applied NAWOA to optimize XGBoost for academic prediction