AI 中文总结
该研究扩展了可解释混合信用评分框架，在台湾和Zindi数据集上验证其性能，开展细粒度公平性审计，揭示社会经济维度的分配违规，可为非洲数字信贷监管提供工具。
AI 中文摘要
我们从三个方面扩展了一种残差学习混合信用评分框架（逻辑回归评分卡加上对其残差的梯度提升校正，每次预测时分解为可解释性比率ρ(x)，用于衡量线性分支的贡献占比）：一是基于Zindi非洲金融包容数据集（肯尼亚、卢旺达、坦桑尼亚、乌干达）的东非实证实例；二是针对框架三个可解释性区域的细粒度公平性审计；三是薄文件细分分析。在用于连续性研究的台湾信用违约基准上，经校准的混合模型达到AUC=0.776（与单独逻辑回归相比AUC提升0.057，与单独XGBoost相比提升0.001），Brier分数降低23%，且将最高违约率的借款人（69.5%）集中在完全可解释区域。在Zindi数据集上，经校准的混合模型达到AUC=0.869（与LR相比AUC提升0.015，p<0.001；与XGBoost相比降低0.004），Brier分数从0.158降至0.085（降幅46%），并复制了区域分配模式。公平性审计发现，在社会经济维度上存在严重的不透明机器学习驱动区域分配：农村受访者比城市受访者低18个百分点，初等及以下教育程度者比中等及以上教育程度者低32个百分点，乌干达受访者比肯尼亚受访者低22个百分点，而性别几乎无分配差异。该审计流程揭示了聚合公平性指标遗漏的子群体分配违规，其形式可直接被非洲各国央行的数字信贷监管机构使用。
英文摘要
We extend a residual-learning hybrid credit scoring framework (logistic regression scorecard plus a gradient-boosting correction on its residuals, decomposed at each prediction into an interpretability ratio $ρ(x)$ that measures the share attributable to the linear branch) along three axes: an East African empirical instantiation on the Zindi Financial Inclusion in Africa data (Kenya, Rwanda, Tanzania, Uganda); a fairness audit at the granularity of the framework's three interpretability regions; and a thin-file segmentation analysis. On the Taiwan Credit Default benchmark retained for continuity, the calibrated hybrid attains AUC $= 0.776$ ($Δ\mathrm{AUC} = +0.057$ vs.\ standalone logistic regression, $+0.001$ vs.\ standalone XGBoost), reduces Brier Score by 23\%, and concentrates the highest-default-rate borrowers (69.5\%) in the fully interpretable region. On Zindi, the calibrated hybrid attains AUC $= 0.869$ ($Δ\mathrm{AUC} = +0.015$ vs.\ LR, $p < 0.001$; $-0.004$ vs.\ XGBoost), cuts Brier from $0.158$ to $0.085$ (a 46\% reduction), and replicates the regional routing pattern. The fairness audit detects severe routing into the opaque ML-driven region along socioeconomic axes: rural respondents by 18 percentage points relative to urban, primary-or-less-educated by 32 points relative to secondary-and-above, and Ugandan respondents by 22 points relative to Kenyan, while gender shows essentially no routing disparity. The audit pipeline surfaces subgroup-routing violations that aggregate fairness metrics miss, in a form directly usable by African central-bank supervisors of digital credit.
