Financial institutions have had a difficult time adapting to the latest regulatory guidance regarding model validation and management. But making the right improvements can also translate into better analytic performance and risk management.
To both comply and compete, it's critical to build an organizational policy for comprehensive model and credit policy management. This framework should include the following tried-and-true practices:
- Have clearly stated credit policies; review these regularly. We recommend reviewing these every six months since they have a direct impact on your bottom line. In the US, the Fed and OCC require a review of policies at least annually.
- Prepare a suitable data sample. Regulators require you demonstrate your model validation sampling techniques are complete, responsible and relevant, since incorrect or inaccurate sampling can impact model performance.
- Ensure model segmentation transparency. In general, you’ll need to clearly document how you segmented subpopulations and how this supports business objectives. Automated tools can help ensure transparency of segmentation logic for regulators, while enabling performance improvements.
- Choose the right model type. It’s important to not only select a model type that's appropriate for the decision type and available data, but one that enables transparency and palatability to both regulators and customers.
- Validate model effectiveness. Revalidate models on an ongoing basis—minimum once a year, but more often in a dynamic economy and/or where account volumes are sufficient to give reliable results.
- Track performance. Employ standard reporting and analysis that provide insight into the health of models that drive your critical decisions.
- Defend decision strategies. Regulators will ask for empirical evidence to justify your decision strategies, and they’ll want to know your realized gains, losses and exposure. Since decision strategies have become increasingly complex, interactive strategy exploration functionality is essential for tracking strategies, strategy changes and results.
- Monitor overrides. Be able to prove that overrides are based on clear and consistent guidelines.
- Document thoroughly. Track everything in your model development and monitoring processes. Build a detailed inventory of every model, along with their purposes, usage, restrictions, inputs, performance, updates, owners within the organization and audit history. By automating production and review of standard reports, you'll free up analysts to focus on ad hoc regulator queries and new model developments.
