Skip to main content
Response to discussion on machine learning for IRB models
Go back1: Do you currently use or plan to use ML models in the context of IRB in your institution? If yes, please specify and answer questions 1.1, 1.2, 1.3. 1.4; if no, are there specific reasons not to use ML models? Please specify (e.g. too costly, interpretability concerns, certain regulatory requirements, etc.)
Please refer to the attached document.1.1: For the estimation of which parameters does your institution currently use or plan to use ML models, i.e. PD, LGD, ELBE, EAD, CCF?
Please refer to the attached document.1.2: Can you specify for which specific purposes these ML models are used or planned to be used? Please specify at which stage of the estimation process they are used, i.e. data preparation, risk differentiation, risk quantification, validation.
Please refer to the attached document.1.3: Please also specify the type of ML models and algorithms (e.g. random forest, k-nearest neighbours, etc.) you currently use or plan to use in the IRB context?
Please refer to the attached document.1.4: Are you using or planning to use unstructured data for these ML models? If yes, please specify what kind of data or type of data sources you use or are planning to use. How do you ensure an adequate data quality?
Please refer to the attached document.2: Have you outsourced or are you planning to outsource the development and implementation of the ML models and, if yes, for which modelling phase? What are the main challenges you face in this regard?
Please refer to the attached document.3: Do you see or expect any challenges regarding the internal user acceptance of ML models (e.g. by credit officers responsible for credit approval)? What are the measures taken to ensure good knowledge of the ML models by their users (e.g. staff training, adapting required documentation to these new models)?
Please refer to the attached document.4: If you use or plan to use ML models in the context of IRB, can you please describe if and where (i.e. in which phase of the estimation process, e.g. development, application or both) human intervention is allowed and how it depends on the specific use of the ML model?
Please refer to the attached document.5. Do you see any issues in the interaction between data retention requirements of GDPR and the CRR requirements on the length of the historical observation period?
Please refer to the attached document.6.a) Methodology (e.g. which tests to use/validation activities to perform).
Please refer to the attached document.6.b) Traceability (e.g. how to identify the root cause for an identified issue).
Please refer to the attached document.6.c) Knowledge needed by the validation function (e.g. specialised training sessions on ML techniques by an independent party).New textarea
Please refer to the attached document.6.d) Resources needed to perform the validation (e.g. more time needed for validation)?
Please refer to the attached document.7: Can you please elaborate on your strategy to overcome the overfitting issues related to ML models (e.g. cross-validation, regularisation)?
Please refer to the attached document.8: What are the specific challenges you see regarding the development, maintenance and control of ML models in the IRB context, e.g., when verifying the correct implementation of internal rating and risk parameters in IT systems, when monitoring the correct functioning of the models or when integrating control models for identifying possible incidences?
Please refer to the attached document.9: How often do you plan to update your ML models (e.g., by re estimating parameters of the model and/or its hyperparameters) Please explain any related challenges with particular reference to those related to ensuring compliance with Regulation (EU) No 529/2014 (i.e. materiality assessment of IRB model changes).
Please refer to the attached document.10: Are you using or planning to use ML for credit risk apart from regulatory capital purposes? Please specify (i.e. loan origination, loan acquisition, provisioning, ICAAP).
Please refer to the attached document.11. Do you see any challenges in using ML in the context of IRB models stemming from the AI act?
Please refer to the attached document.12. Do you see any additional challenge or issue that is relevant for discussion related to the use of ML models in the IRB context?
Please refer to the attached document.13: Are you using or planning to use ML for collateral valuation? Please specify.
Please refer to the attached document.14. Do you see any other area where the use of ML models might be beneficial?
Please refer to the attached document.15: What does your institution do to ensure explainability of the ML models, i.e. the use of ex post tools to describe the contribution of individual variables or the introduction of constraints in the algorithm to reduce complexity?
Please refer to the attached document.16. Are you concerned about how to share the information gathered on the interpretability with the different stakeholders (e.g. senior management)? What approaches do you think could be useful to address these issues?
Please refer to the attached document.17: Do you have any concern related to the principle-based recommendations?
Please refer to the attached document.Name of the organization
European Association of Co-operative Banks (EACB)
