Paper: arXiv 2610.13199

Authors: Dian Prinsloo, Tanja Verster, Neill Smit

Abstract

Background: Credit risk modelling is fundamental in financial institutions, typically using credit history, repayment behaviour, income, and outstanding debt to estimate a borrower’s probability of default. Although transactional data are sometimes incorporated through aggregated measures such as recency, frequency, and monetary indicators, behavioural information embedded in raw transaction narratives remains largely unexplored due to its unstructured nature. This limits opportunities to extract richer behavioural insights. Aim: This research investigates payment narratives from transactional data as an alternative data source for credit risk modelling. Setting: The study uses transactional data from a large South African financial institution focused on small and medium enterprises. Method: Techniques such as natural language processing and regular expressions are used to transform unstructured transaction descriptions into meaningful, explainable behavioural features by categorising transactions into interpretable spending categories. A novel categorisation algorithm was developed and evaluated for classification accuracy. The extracted features are incorporated into a credit risk scorecard to assess their predictive value. Results: The categorisation algorithm demonstrates high classification accuracy. Using these features in the scorecard resulted in a significant increase in Gini compared to a scorecard without them. Conclusion: Text-based transactional information can be systematically extracted, categorised, and operationalised to enhance credit risk model performance. Contribution: The study develops a novel, integrated, explainable methodology for transforming transactional text into behavioural features, introduces a structured RegEx-based categorisation approach, and demonstrates their predictive value within traditional scorecard frameworks.

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper presents a novel approach to feature engineering from transactional data, demonstrating strong empirical results. While the methodology is clearly explained, the mathematical complexity is moderate, focusing more on practical application than theoretical derivations. The study’s focus on real-world data and measurable impact on credit scoring is a significant strength.

Research Flowchart

  flowchart TD
    A[Research Goal: Enhance Credit Risk Scorecards with Transactional Behavioural Features] --> B(Data Input: Transactional Payment Narratives from SA Financial Institution);
    B --> C{Computational Process: NLP & RegEx for Categorisation};
    C --> D[Methodology: Develop Novel Categorisation Algorithm];
    D --> E(Outcome 1: High Classification Accuracy of Algorithm);
    E --> F[Methodology: Integrate Features into Credit Risk Scorecard];
    F --> G(Outcome 2: Significant Gini Increase in Scorecard);
    G --> H[Conclusion: Text-based transactional info systematically enhances credit risk models];