模型虽隐藏性别，仍能通过婚姻、年龄等特征猜出用户性别，导致信贷歧视。
Structural Gender Bias in Credit Scoring: Proxy Leakage
- 用SHAP分析发现婚姻、年龄、信用额度是性别代理变量。
- 仅凭非敏感特征就能以0.65的AUC复原性别，证明偏见未消除。
- 建议从统计公平转向因果建模，防范结构性歧视。
随着金融机构越来越多地采用机器学习进行信用风险评估，算法偏见的持续存在仍是实现公平金融包容性的关键障碍。本研究对台湾信用违约数据集中的结构性性别偏见进行了全面审计，挑战了‘通过忽视实现公平’的主流观念。尽管已移除明确的受保护属性并应用行业标准的公平性干预措施，结果表明性别化预测信号仍深度嵌入非敏感特征中。利用SHAP（SHapley Additive exPlanations），我们发现婚姻状况、年龄和信用额度等变量作为性别的重要代理特征，使模型在保持统计公平性的同时仍保留歧视路径。为数学量化这种泄漏，我们采用对抗性逆向建模框架。结果显示，仅通过纯非敏感金融特征即可以0.65的ROC AUC得分重构性别属性，表明传统公平性审计无法检测隐性结构性偏见。这些发现倡导从表面统计均等到因果感知建模与结构问责的转变。
原文摘要 · Abstract (English)
As financial institutions increasingly adopt machine learning for credit risk assessment, the persistence of algorithmic bias remains a critical barrier to equitable financial inclusion. This study provides a comprehensive audit of structural gender bias within the Taiwan Credit Default dataset, specifically challenging the prevailing doctrine of "fairness through blindness." Despite the removal of explicit protected attributes and the application of industry standard fairness interventions, our results demonstrate that gendered predictive signals remain deeply embedded within non-sensitive features. Utilizing SHAP (SHapley Additive exPlanations), we identify that variables such as Marital Status, Age, and Credit Limit function as potent proxies for gender, allowing models to maintain discriminatory pathways while appearing statistically fair. To mathematically quantify this leakage, we employ an adversarial inverse modeling framework. Our findings reveal that the protected gender attribute can be reconstructed from purely non-sensitive financial features with an ROC AUC score of 0.65, demonstrating that traditional fairness audits are insufficient for detecting implicit structural bias. These results advocate for a shift from surface-level statistical parity toward causal-aware modeling and structural accountability in financial AI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。