Cost-Bounded, Accuracy-Aware Hyperparameter Optimization Integrated with Rule-Based Book Recommendation for Developer Profiling on Stack Overflow
TL;DR
Experimental results show that the proposed method achieves the highest macro-averaged precision and significantly outperforms classical baselines while remaining competitive with state-of-the-art modelbased approaches, demonstrating the effectiveness of the proposed framework in delivering personalized learning resources.
Abstract
This paper introduces HyperR, an integrated framework that combines hyperparameter optimization with a rule-based book recommender for developer profiling on Stack Overflow. The proposed optimizationmethod employs a cost-bounded, accuracy-aware strategy with early stopping and adaptive search to balance computational efficiency and search effectiveness. The framework evaluates both model-free (Grid Search, Random Search, Nelder–Mead, DEoptim) and model-based (Bayesian Optimization, AutoFT, mlrMBO,TuRBO) optimizers across multiple classifiers on a dataset of 20,000 Stack Overflow questions, using stratified 70/30 train-test splits with 20 repeated runs per configuration. Experimental results show that the proposed method achieves the highest macro-averaged precision (0.671) and significantly outperformsclassical baselines (adjusted p < 0.008), while remaining competitive with state-of-the-art modelbased approaches (adjusted p > 0.05). In addition, it reduces peak memory usage by up to 25% compared with exhaustive search methods. The recommendation module achieves strong performance (Precision@3= 0.82 and Recall@3 = 0.77), demonstrating the effectiveness of the proposed framework in delivering personalized learning resources.