Paper: arXiv 2507.15441

Authors: Arno Botha, Tanja Verster

Abstract

Under the International Financial Reporting Standards (IFRS) 9, credit losses ought to be recognised timeously and accurately. This requirement belies a certain degree of dynamicity when estimating the constituent parts of a credit loss event, most notably the probability of default (PD). It is notoriously difficult to produce such PD-estimates at every point of loan life that are adequately dynamic and accurate, especially when considering the ever-changing macroeconomic background. In rendering these lifetime PD-estimates, the choice of modelling technique plays an important role, which is why we first review a few classes of techniques, including the merits and limitations of each. Our main contribution however is the development of an in-depth and data-driven tutorial using a particular class of techniques called discrete-time survival analysis. This tutorial is accompanied by a diverse set of reusable diagnostic measures for evaluating various aspects of a survival model and the underlying data. A comprehensive R-based codebase is further contributed. We believe that our work can help cultivate common modelling practices under IFRS 9, and should be valuable to practitioners, model validators, and regulators alike.

Complexity vs Empirical Score

  • Math Complexity: 5.5/10
  • Empirical Rigor: 8.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: This paper presents a exceptionally clear and thorough tutorial on discrete-time survival analysis for IFRS 9 PD term-structure modeling. It achieves remarkable empirical rigor and reproducibility by employing real-world South African mortgage data alongside a fully publicly available, reusable R codebase.

Research Flowchart

  flowchart TD
    A[Goal: Develop Dynamic Lifetime PD-Estimates for IFRS 9 Compliance] --> B[Review & Select Modeling Class: Discrete-Time Survival Analysis]
    B --> C[Inputs: Loan-Level Data & Dynamic Macroeconomic Factors]
    C --> D[Model Development & Implementation via R Codebase]
    D --> E[Model Evaluation using Diagnostic Measures]
    E --> F[Outcomes: Practical Tutorial, R Codebase & Standardized IFRS 9 Framework]

Cited References (77)

  1. Defining and comparing SICR-events for classifying impaired loans under IFRS 9 — → 2303.03080
  2. A procedure for loss-optimising the timing of loan recovery under uncertainty (2021) — link
  3. Modelling the term-structure of default risk under IFRS 9 within a multistate regression framework — → 2502.14479
  4. Towards modelling lifetime default risk: Exploring different subtypes of recurrent event cox-regression models (2025) — link
  5. Approaches for modelling the term-structure of default risk under IFRS 9 : A tutorial using discrete-time survival analysis [Source Code] (2025) — link
  6. Simulation-based optimisation of the timing of loan recovery across different portfolios (2021) — link
  7. Credit Risk Management: Basic Concepts (2009) — link
  8. Applied Logistic Regression (2000) — link
and 69 more
  1. Survival analysis: a self-learning text (2012) — link
  2. Survival analysis (2005)
  3. Modeling survival data: extending the Cox model (2000) — link
  4. Multivariate survival analysis and competing risks (2012)
  5. Credit Scoring and Its Applications (2017)
  6. Credit risk analytics: Measurement techniques, applications, and examples in SAS (2016)
  7. Pattern recognition and machine learning (2006)
  8. An introduction to statistical learning: with applications in R (2013) — link
  9. Credit Risk Scorecards: Developing and Implementing Intelligent Credit Scoring (2005)
  10. Survival Analysis Using SAS: A Practical Guide (2010) — link
  11. International Convergence of Capital Measurement and Capital Standards: A Revised Framework, Comprehensive Version (2006) — link
  12. The Basel Framework (2019) — link
  13. International Financial Reporting Standard ( IFRS ) 9: Financial Instruments (2014) — link
  14. Regulation (EU) No 575/2013 of the European Parliament and of the Council of 26 June 2013 on prudential requirements for credit institutions and investment firms and amending Regulation (EU) No 648/2012 Text with EEA relevance (2013) — link
  15. Household debt (indicator) (2018) — link
  16. Estimating Lifetime Expected Credit Losses Under IFRS 9 (2016) — link
  17. A Review on the Probability of Default for IFRS 9 (2021) — link
  18. Impairment of Financial Instruments under IFRS 9 (2014) — link
  19. IFRS 9 : Expected Credit Losses (2014) — link
  20. Credit risk term-structures for Lifetime Impairment Forecasting: A practical guide (2017) — link
  21. IFRS 9 and CECL Credit Risk Modelling and Validation: A Practical Guide with Examples Worked in R and SAS (2019)
  22. Survival analysis (2016) — link
  23. Survival analysis and interpretation of time-to-event data: the tortoise and the hare (2018) — link
  24. It’s d 'e j `a vu all over again: Using multiple-spell discrete-time survival analysis (1995) — link
  25. An introduction to ROC analysis (2006) — link
  26. Time-dependent ROC curves for censored survival data and a diagnostic marker (2000) — link
  27. Development of an Impairment Point in Time Probability of Default Model for Revolving Retail Credit Products: South African Case Study (2021) — link
  28. Modelling recurrent events: a tutorial for analysis in epidemiology (2015) — link
  29. A systematic comparison of recurrent event models for application to composite endpoints (2018) — link
  30. Regression models and life-tables (1972)
  31. It’s about time: Using discrete-time survival analysis to study duration and the timing of events (1993)
  32. Survival prediction models: an introduction to discrete-time modeling (2022) — link
  33. Survival analysis: the importance of censored observations (1996) — link
  34. Multihorizon discrete time survival models (2022) — link
  35. Lifetime PD Analytics for Credit Portfolios: A Survey (2016) — link
  36. Point-in-Time PD Term Structure Models for Multi-Period Scenario Loss Projection: Methodologies and Implementations for IFRS 9 ECL and CCAR Stress Testing (2017) — link
  37. Calculating Basel II Risk Parameters for a Portfolio of Retail Loans (2003)
  38. Nonparametric Estimation from Incomplete Observations (1958)
  39. Survival analysis and the credit granting decision (1992)
  40. Not if but when will borrowers default (1999) — link
  41. Survival analysis methods for personal loan data (2002) — link
  42. Credit scoring with macroeconomic variables using survival analysis (2009) — link
  43. Forecasting and stress testing credit card default using dynamic models (2013)
  44. Retail credit stress testing using a discrete hazard model with macroeconomic factors (2014) — link
  45. Time to default in credit scoring using survival analysis: a benchmark study (2017) — link
  46. Time Varying and dynamic models for default risk in consumer loans (2010)
  47. Intensity models and transition probabilities for credit card loan delinquencies (2014) — link
  48. Incorporating heterogeneity and macroeconomic variables into multi-state delinquency models for credit cards (2018) — link
  49. Dynamic survival models with varying coefficients for credit risks. (2019) — link
  50. Forecasting losses on a liquidating long-term loan portfolio (1995) — link
  51. Markov chain models for delinquency: Transition matrix estimation and forecasting (2011) — link
  52. The predictive accuracy of Sukuk ratings; Multinomial Logistic and Neural Network inferences (2015) — link
  53. Tutorial in biostatistics: competing risks and multi-state models (2007) — link
  54. Consistent estimation of the expected Brier score in general survival models with right-censored data (2006) — link
  55. Assessment and comparison of prognostic classification schemes for survival data (1999) — link
  56. Review of Statistical Methods for Evaluating the Performance of Survival or Other Time-to-Event Prediction Models (from Conventional to Deep Learning Approaches) (2021) — link
  57. riskRegression : Risk Regression Models and Prediction Scores for Survival Analysis with Competing Risks (2025) — link
  58. pec : Prediction Error Curves (2021) — link
  59. A review of spline function procedures in R (2019) — link
  60. A pragmatic macroeconomic default risk adjustment in developing countries (2025) — link
  61. A Forward-Looking IFRS 9 Methodology, Focussing on the Incorporation of Macroeconomic and Macroprudential Information into Expected Credit Loss Calculation (2023) — link
  62. A tutorial on evaluating the time-varying discrimination accuracy of survival models used in dynamic decision making (2018) — link
  63. Nearest neighbor estimation of a bivariate distribution under random censoring (1994) — link
  64. The good, the bad and the impaired: A credit risk model of the Irish mortgage market (2016) — link
  65. A comprehensive study of coefficient signs in weighted logistic regression (2024) — link
  66. Learning from imbalanced data (2009) — link
  67. Multinomial logistic regression and spline regression for credit risk modelling (2018) — link
  68. Joint modeling: An application in behavioural scoring (2018) — link
  69. Joint models for longitudinal and discrete survival data in credit scoring (2023) — link

2 of 77 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.