<p>Credit risk assessment plays a crucial role in financial decision-making, but imbalanced datasets present significant challenges, leading to biased predictions and poor classification of defaulters. Traditional techniques such as under-sampling, over-sampling, and SMOTE aim to address this imbalance but suffer from issues like information loss, lack of diversity, and duplicated patterns. To address these issues, we propose a novel two-stage classification framework that integrates a Voting Classifier with Meta-Dynamic Ensemble Selection (Meta-DES). The first stage employs a voting classifier to make confident predictions while isolating ambiguous instances. The second stage applies Meta-DES to dynamically select the most competent classifiers based on meta-features and the region of competence. This approach enhances classification performance by refining uncertain predictions through meta-learning and leveraging ensemble techniques to improve robustness. Extensive experimentation on a real-world loan application dataset demonstrates that our approach significantly outperforms traditional machine learning models. Our method maintains reliable predictions as demonstrated by comprehensive performance evaluations. The proposed model achieves superior precision and recall, outperforming traditional classifiers. Experimental results highlight its balanced performance in distinguishing defaulters and non-defaulters, achieving an accuracy of 0.8332, with significantly improved F1 scores. Additionally, statistical validation using the McNemar test confirms the superiority of our approach over baseline models, with overwhelmingly significant results. By effectively reducing Type I and Type II errors, our approach enhances financial risk assessment and supports more reliable credit decision-making. The proposed methodology not only improves classification outcomes but also contributes to minimizing financial losses and optimizing lending strategies.</p>