1 / 8

Challenges in Validation: Taking the Study Findings Forward A Corporate Perspective

Challenges in Validation: Taking the Study Findings Forward A Corporate Perspective. Advanced IRB Forum New York, June 19, 2003. Lyn McGowan RBC Financial Group. The Challenge of Validation for Corporate and Mid-Market Portfolios.

raphael
Download Presentation

Challenges in Validation: Taking the Study Findings Forward A Corporate Perspective

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Challenges in Validation: Taking the Study Findings ForwardA Corporate Perspective Advanced IRB Forum New York, June 19, 2003 Lyn McGowan RBC Financial Group

  2. The Challenge of Validation for Corporate and Mid-Market Portfolios • Internal rating validation approaches, methods, issues vary, depending on the types of rating models used • Rating system design and validation go hand in hand Type of Rating ModelCORPORATEMID-MARKET Statistical Models 7 4 External Vendor Models 7 2 Expert Judgement Models 15 11 Hybrid Models 10 7

  3. The Data Challenge • Insufficient data to rely on purely statistical means of validation  must rely on other means • The Basel Research Task Force recognizes that quantitative statistical techniques should be performed, however should not drive the pass/fail decision for IRB validation • Supervisor will need to understand and be satisfied with: • The logic of the risk assessment process • The rating system’s design and operation • How the rating system has been calibrated • The internal validation process • The “feedback loop”

  4. Logic of the Risk Assessment Process • Conceptual clarity  Well-defined drivers/factors  Dynamic properties, significance of factors • Transparency Explicitly demonstrates reasoning  Constraints (such as stipulated factor weightings)  Assessment horizon • Replicability  “Gut feel” won’t do  Criteria or thresholds for factors • Well-documented  Process/procedures manual

  5. Rating System Design and Operation • Conceptual clarity  Understandable output • Transparency  Not a Black Box • Replicability  Well-defined framework and/or methodology • Consistency  Application across industry, geography • Documentation  Rationale for design  Conceptual meaning, definition of grades  Frequency of review  Override authority, reporting

  6. Calibration of the Rating System • Conceptual clarity  Techniques have been combined rationally • Transparency  Availability of data across quality spectrum  Method of mitigating scarcity of data  Basis for numerator and denominator • Consistency  Potential sources of bias  Relevance of external data • Documentation  Specific techniques used

  7. Internal Validation Process • Conceptual clarity  Discriminative power vs accuracy of calibration  Factor relevance vs factor weights vs model strength  Rationale for Triangulation • Transparency  Scope / frequency of work  Mapping processes  Objective metrics • Consistency  Actual vs predicted  Own to external loss experience  Role of loan review unit • Documentation  Clear, comprehensive, precise

  8. The Critical Feedback Loop Calibration Continuous Improvement Cycle Validation

More Related