Creditworthiness Assessment Model
When using automated models for Creditworthiness assessment and credit decision-making, institutions should understand the models used, and their methodology, input data, assumptions, limitations and outputs, and should have in place:
- internal policies and procedures detecting and preventing bias and ensuring the quality of the input data;
- measures to ensure the traceability, auditability, and robustness and resilience of the inputs and outputs;
- internal policies and procedures ensuring that the quality of the model output is regularly assessed, using measures appropriate to the model’s use, including backtesting the performance of the model;
- control mechanisms, model Overrides and escalation procedures within the regular credit decision-making framework, including qualitative approaches, qualitative risk assessment tools (including expert judgement and critical analysis) and quantitative limits.
Institutions should have adequate model documentation that covers:
- methodology, assumptions and data inputs, and an approach to detecting and preventing bias and ensuring the quality of input data;
- the use of model outputs in the decision-making process and the monitoring of these automated decisions on the overall quality of the portfolio or products in which these models are used.
- EBA, Guidelines on loan origination and monitoring EBA/GL/2020/06