Gartner’s analytic value escalator identifies four different types of analytics, ordered by their level complexity and business value (level 1 being the least complex, but least valuable analytic type):

1. Descriptive
2. Diagnostic
3. Predictive
4. Prescriptive

According to Gartner, prescriptive analytics is the gold standard. That’s because prescriptive analytics help teams and organizations answer a key question everybody faces, How can we make it happen? In the credit risk arena, the answer to this question is risk strategy.

Credit risk strategy is what follows scorecard development but precedes scorecard implementation. Credit risk strategy tells teams how to interpret customer scores and what action should be taken as a result. When implemented correctly, a winning credit risk strategy increases the customer base, reduces credit risk, and maximizes profit.

But before beginning strategy analysis and running what-if scenarios, it’s important to identify business objectives and understand the business processes that shape strategy analyses. The simplest, most common form of credit risk strategy is based on a one-dimensional cut-off for an accept or reject decision. The cut-off level (the minimum score for credit approval) can be a hard cut-off with a single fixed value, or it can have adjustable values with multiple treatments such as unconditional accept, conditional accept, or reject. Often, lenders use a segmentation strategy to identify different cut-off levels across customer segments; and lenders can carry out segmentation via many factors, including region, demographics, channel distributions, or previously declined customers. For example, strategy segmentation can be based on the same bad rate across customer segments, benefiting from higher approval rates for better segments, or the same approval rate can be preserved across all segments, resulting in lower bad debt across better segments.

Cut-off levels depend on business objectives. For example, if the objective is based on retaining an 80% acceptance rate, the retrospective analysis may specify the cut-off value to be 320. But if the objective is based on a maximum default rate of 6%, the strategy could be even more restrictive and the cut-off level increased to 360. If the strategy is based on a pure profit/loss measurement, this would require setting the cut-off score to 440, per the example in Figure 1.

Figure 1. Different Cut-off Strategies

More sophisticated credit risk strategies have multiple cut-off levels, or combine two or more credit scores (like internal application score and bureau scores, for example). Often, strategies include other predictive models like customer retention/response rate or customer lifetime value. These behavioral scores – combined with policy and regulatory rules and business key performance indicators (KPIs) – can help organizations take advantage of predictive analytics and business rules.

Figure 2. Multiple Cut-off Levels for Multiple Treatments

And organizations can also use scores for risk-based pricing to adjust product offers like interest rates, credit limits, repayment terms, and more. Risk-based pricing takes many forms: from one-dimensional multiple cut-off treatments based on profit/loss analysis (for example, accept with lower limit), to a matrix approach combining two dimensions, for example behavioral score and outstanding balance to identify credit limits or interest rates. Teams can also adopt the matrix approach for a simple optimization to control operational costs. For example, combining two predictive models – scores and response rate – may help marketing departments focus on low-risk customers who are likely to respond to an offer. 

Figure 3. Risk-based Pricing using Matrix Approach

Figure 4. Retention and Risk Segmentation Strategy

But there’s danger in using an over-simplified strategy. For example, the strategy may reject risky customers that would’ve been loyal or highly profitable. A customer lifetime value (CLV) model helps identify valuable segments; but lenders can be reluctant to use CLV since it can be extremely difficult to determine. In such situations, a thorough insight analysis may help identify valuable segments and help organizations adjust their strategy accordingly.

Conclusion

Credit scoring is a dynamic, flexible, and powerful tool for lenders, but there are plenty of ins and outs that are worth covering in detail. To learn more about credit scoring and credit risk mitigation techniques, read the next installment of our credit scoring series, Part Nine: Scorecard Implementation - Deployment, Production, and Monitoring. 

And click here to learn more about Altair’s credit scoring, credit risk, and financial services solutions.

Read prior Credit Scoring Series installments:

• Part One: Introduction to Credit Scoring
• Part Two: Credit Scorecard Modeling Methodology
• Part Three: Data Preparation and Exploratory Data Analysis
• Part Four: Variable Selection
• Part Five: Credit Scorecard Development
• Part Six: Segmentation and Reject Inference
• Part Seven: Additional Credit Risk Modeling Considerations