KPMG provides sophisticated model development and validation solutions for all major risk types, as well tailor-made solutions covering client needs in the financial industry. The methodologies followed include both traditional model development techniques as well as advanced Artificial Intelligence/Machine Learning (AI/ML) statistical techniques and algorithms that offer improved model performance while maintaining interpretable results.
An indicative and non-exhaustive list of areas that our quantitative model solutions can efficiently help clients is the following:
- Credit risk models, such as Probability of Default (PD), Loss Given Default (LGD), Exposure at Default (EAD) that feed into the Expected Credit Loss (ECL) estimation, both under the IFRS 9 and Internal Ratings-based (IRB) frameworks.
- Market risk models, such as Value-At-Risk (VaR) and Expected Shortfall (ES) both for internal and regulatory Stress Testing, as well for capital calculation purposes.
- Counterparty Credit Risk models, such as Potential Future Exposure (PFE), Exposure at Default (EAD), Credit Valuation Adjustment (CVA), Debt Valuation Adjustment (DVA) under various methodologies and techniques.
- Operational Risk Models, targeting at regulatory capital estimation (e.g., based on the Advanced Measurement Approach- AMA), potential losses from failures of systems and processes, and fraud detection.
- Pricing models, both for loan portfolio valuation purposes (performing/non-performing, secured/unsecured exposures), as well as for financial derivatives’ valuation, such as options, swaps, forwards, futures, across various asset types (Equity, Interest Rate, Foreign Exchange, Credit, Commodities).
- Development of challenger models for benchmarking purposes across all major risk types and based on best global practices.
- Development of Early Warning Systems, aiming at providing qualitative and quantitative indicators based on appropriate risk characteristics that allow for early measures against hazardous events, e.g., credit distresses and defaults, liquidity draining, frauds etc.
- Integration of ESG factors in risk models for economic and regulatory capital calculation purposes.
- Application of state-of-the-art risk analytics for the development and automation of risk tools and corresponding solutions.
