Enhancing credit risk scorecards with transactional-based behavioural features
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.
Related
- Learned Monotone Recurrent Features in Governed Credit Scoring: The Price of the Frame and the Necessity of Macro Conditioning
- Acculturation as a Situated Transactional Process
- Credit Spreads' Term Structure: Stochastic Modeling with CIR++ Intensity
- A Multimetric Evaluation of Ensemble and Neural Models for Imbalanced Credit Scoring on the German Credit Dataset
- Persistence, Exposure, and Credit Routing in Linear Temporal Predictive Coding
BibTeX
@misc{prinsloo2026enhancing,
title = {{Enhancing credit risk scorecards with transactional-based behavioural features}},
author = {Dian Prinsloo and Tanja Verster and Neill Smit},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.13199},
eprint = {2610.13199},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.13199},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Enhancing credit risk scorecards with transactional-based behavioural features
AU - Dian Prinsloo
AU - Tanja Verster
AU - Neill Smit
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2610.13199
UR - https://arxiv.org/abs/2610.13199
AB - 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.
ER -