With the rapid development of fintech, the need for dynamic credit risk evaluation is becoming increasingly important. While previous studies on credit scoring have mostly focused on single-period loan default prediction, we call for a new avenue—multiperiod default prediction (MPDP)—to depict risk profiles over time. To address the challenges raised by MPDP, such as monotonic default probability prediction and complex relationship accommodation, we propose a novel approach, hybrid and collective scoring (HACS). We design a hybrid modeling strategy to predict whether and when a borrower will default separately through a default discrimination model and a default time estimation model, respectively, and synthesize them through a probabilistic framework. To accommodate various possible patterns of default time and measure the distribution of default probability over successive time intervals, we propose a joint default modeling method to train the default time estimation model. Empirical evaluations at the model (time-to-default prediction performance and discrimination performance) and mechanism (identifiability and discriminability) levels, as well as impact analyses at the application (granting performance and profitability performance) level, show that HACS outperforms the benchmarked survival analysis and multilabel learning methods on all fronts. It can more accurately predict time-to-default and provide financial institutions and investors better decision-support in granting loans and selecting loan portfolios.

中文翻译：

---

描述随时间变化的风险状况：一种新颖的多期贷款违约预测方法

随着金融科技的快速发展，动态信用风险评估的需求变得越来越重要。虽然之前的信用评分研究主要集中在单期贷款违约预测上，但我们呼吁采用新的途径——多期违约预测（MPDP）——来描述随时间变化的风险状况。为了解决 MPDP 提出的挑战，例如单调默认概率预测和复杂关系调节，我们提出了一种新方法：混合集体评分（HACS）。我们设计了一种混合建模策略，分别通过违约判别模型和违约时间估计模型来预测借款人是否以及何时违约，并通过概率框架综合它们。为了适应各种可能的违约时间模式并测量连续时间间隔内的违约概率分布，我们提出了一种联合违约建模方法来训练违约时间估计模型。模型（违约时间预测性能和辨别性能）和机制（可识别性和可辨别性）层面的实证评估以及应用程序（授予性能和盈利性能）层面的影响分析表明，HACS 优于基准生存各个方面的分析和多标签学习方法。它可以更准确地预测违约时间，为金融机构和投资者在发放贷款和选择贷款组合方面提供更好的决策支持。