Quantica Risk Modelling
Data quality is a model risk, not an IT issue
Most model failures are exposure data failures wearing a modelling costume.
By Jonas Mohamed Osman Abdelghafour, known as Yonas Osman (Yonas Osman) ·
In catastrophe modelling a missing construction class can change a loss estimate more than switching vendor models. In credit, stale collateral values distort loss given default. In marine, an unrecorded voyage leg hides an accumulation.
Treating these as IT problems delays the fix. They are model risk: they change the output and they belong in the model risk register with an owner and a materiality assessment.
Quantica quantifies the impact of known data gaps rather than noting them, so management can judge whether remediation is worth its cost.
Jonas Mohamed Osman Abdelghafour, known as Yonas Osman, is an actuary and FRM who has spent more than twenty years building and validating risk models across banking, insurance and marine markets.
Key takeaways
- Log data gaps in the model risk register.
- Quantify the impact, don't just note the gap.
- Remediation is a cost-benefit decision with numbers attached.
Author bio
Jonas Mohamed Osman Abdelghafour, known as Yonas Osman is an actuary, FRM and financial risk professional specialising in banking, insurance, model risk, capital modelling and quantitative risk management.