Paper: arXiv 2603.26309

Authors: Victor Medina-Olivares, Wangzhen Xia, Stefan Lessmann, Nadja Klein

Abstract

We propose a semi-structured discrete-time multi-state model to analyse mortgage delinquency transitions. This model combines an easy-to-understand structured additive predictor, which includes linear effects and smooth functions of time and covariates, with a flexible neural network component that captures complex nonlinearities and higher-order interactions. To ensure identifiability when covariates are present in both components, we orthogonalise the unstructured part relative to the structured design. For discrete-time competing transitions, we derive exact transformations that map binary logistic models to valid competing transition probabilities, avoiding the need for continuous-time approximations. In simulations, our framework effectively recovers structured baseline and covariate effects while using the neural component to detect interaction patterns. We demonstrate the method using the Freddie Mac Single-Family Loan-Level Dataset, employing an out-of-time test design. Compared with a structured generalised additive benchmark, the semi-structured model provides modest but consistent gains in discrimination across the earliest prediction spans, while maintaining similar Brier scores. Adding macroeconomic indicators provides limited incremental benefit in this out-of-time evaluation and does not materially change the estimated borrower-, loan-, or duration-driven effects. Overall, semi-structured multi-state modelling offers a practical compromise between transparent effect estimates and flexible pattern learning, with potential applications beyond credit-transition forecasting.

Complexity vs Empirical Score

  • Math Complexity: 6.8/10
  • Empirical Rigor: 7.5/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents a mathematically sound semi-structured multi-state framework that bridges additive models and neural networks via orthogonalisation, while addressing exact competing transition probability mappings. The empirical evaluation is rigorous, using an out-of-time test set on the Freddie Mac loan-level dataset to demonstrate predictive gains without sacrificing interpretability.

Research Flowchart

  flowchart TD
    A[Research Goal: Balance interpretability and predictive power in mortgage delinquency forecasting] --> B[Data Inputs: Freddie Mac Loan-Level Dataset & Macroeconomic Indicators]
    B --> C[Methodology: Semi-structured Discrete-time Multi-state Model]
    C --> D[Computational Core: Combine Additive Predictor + Neural Network with Orthogonalisation]
    D --> E[Mathematical Transformation: Map Binary Logistic Models to Competing Transition Probabilities]
    E --> F[Out-of-Time Model Evaluation & Comparison]
    F --> G[Key Outcomes: Enhanced early discrimination, transparent effect recovery, and stable performance without macro dependency]