结合可解释人工智能（XAI）分析的混合重采样与堆叠集成技术的破产预测
Bankruptcy Prediction via Hybrid Resampling and Stacking Ensemble Techniques with Explainable Artificial Intelligence (XAI)-Driven Analysis
浏览论文内容
中文总结 AI 辅助
本研究提出整合多技术的破产预测框架，在不平衡金融数据中优化少数类检测，经实验验证了模型性能，可助力财务困境企业的早期预警系统建设。
中文摘要 AI 辅助
本研究开发并评估了一种破产预测框架，该框架整合了基于共识的特征选择、混合重采样、堆叠集成以及可解释人工智能，以改进严重不平衡金融数据中的少数类检测。使用来自UCI机器学习仓库的台湾破产预测数据集，首先应用五种特征选择算法，通过共识保留规则将输入空间缩减为23个稳健变量。随后使用SVM-SMOTE、SMOTE-Tomek和SMOTE-ENN生成平衡训练数据。将五种集成机器学习分类器（即梯度提升、极端梯度提升、直方图梯度提升、LightGBM和AdaBoost）与五种深度学习模型（包括RNN、LSTM、GRU、DNN和MLP）进行比较。此外，混合堆叠集成将五种机器学习分类器作为基学习器，每个深度学习模型作为元学习器。使用准确率、召回率、特异度、G-均值和ROC-AUC评估模型性能，同时使用SHAP解释特征贡献。结果表明，重采样策略显著影响模型行为：SVM-SMOTE和SMOTE-Tomek更倾向于准确率和特异度，而SMOTE-ENN则实现更强的少数类检测。在 standalone模型中，采用SMOTE-ENN的GRU实现最佳整体预测平衡，召回率为0.8627，G-均值为0.8517，ROC-AUC为0.9431；在堆叠集成中，采用SMOTE-ENN的（GB+XGB+HGB+LGBM+AB）+LSTM在灵敏度和特异度之间提供最强的折中。SHAP分析确定杠杆率、盈利能力、偿付能力和运营效率指标是破产风险最具影响力的预测因子。这些发现为财务困境企业提供了更可靠、可解释的早期预警系统支持。
英文摘要
This study develops and evaluates a bankruptcy prediction framework that integrates consensus-based feature selection, hybrid resampling, stacking ensembles, and explainable artificial intelligence to improve minority-class detection in severely imbalanced financial data. Using the Taiwanese Bankruptcy Prediction dataset from the UCI Machine Learning Repository, five feature-selection algorithms were first applied, and a consensus retention rule reduced the input space to 23 robust variables. The balanced training data were then generated using SVM-SMOTE, SMOTE-Tomek, and SMOTE-ENN. Five ensemble machine learning classifiers, namely gradient boosting, extreme gradient boosting, histogram-based gradient boosting, LightGBM, and AdaBoost, were compared with five deep learning models, including RNN, LSTM, GRU, DNN, and MLP. In addition, hybrid stacking ensembles combined the five machine learning classifiers as base learners with each deep learning model as a meta-learner. Model performance was assessed using accuracy, recall, specificity, G-mean, and ROC-AUC, while SHAP was used to explain feature contributions. The results show that resampling strategy materially shaped model behavior. SVM-SMOTE and SMOTE-Tomek favored accuracy and specificity, whereas SMOTE-ENN delivered stronger minority-class detection. Among standalone models, the GRU with SMOTE-ENN achieved the best overall predictive balance, with recall of 0.8627, G-mean of 0.8517, and ROC-AUC of 0.9431. Among stacking ensembles, SMOTE-ENN with (GB+XGB+HGB+LGBM+AB)+LSTM provided the strongest compromise between sensitivity and specificity. SHAP analysis identified leverage, profitability, solvency, and operational efficiency indicators as the most influential predictors of bankruptcy risk. These findings support more reliable and interpretable early warning systems for financially distressed firms.
