In my last post, I covered the importance of using quality credit attributes to gain greater accuracy in risk models. Credit attributes are also powerful in strengthening the decision process by providing granular views on consumers based on unique behavior characteristics. Effective uses include segmentation, overlay to scores and policy definition – across the entire customer lifecycle, from prospecting to collections and recovery.
Overlay to scores – Credit attributes can be used to effectively segment generic scores to arrive at refined “Yes” or “No” decisions. In essence, this is customization without the added time and expense of custom model development. By overlaying attributes to scores, you can further segment the scored population to achieve appreciable lift over and above the use of a score alone.
Segmentation – Once you made your “Yes” or “No” decision based on a specific score or within a score range, credit attributes can be used to tailor your final decision based on the “who”, “what” and “why”. For instance, you have two consumers with the same score. Credit attributes will tell you that Consumer A has a total credit limit of $25K and a BTL of 8%; Consumer B has a total credit limit of $15K, but a BTL of 25%. This insight will allow you to determine the best offer for each consumer.
Policy definition - Policy rules can be applied first to get the desirable universe. For example, an auto lender may have a strict policy against giving credit to anyone with a repossession in the past, regardless of the consumer’s current risk score.
High quality attributes can play a significant role in the overall decision making process, and its expansive usage across the customer lifecycle adds greater flexibility which translates to faster speed to market. In today’s dynamic market, credit attributes that are continuously aligned with market trends and purposed across various analytical projects are essential to delivering better decisions.