There is no shortage of data when it comes to a credit union's credit card program. Every day there is a tidal wave of data about who used their cards, how many times, what they spent and where they spent it. And separately, there is almost as much data available about potential cardholders that a credit union might want to target among its membership.
The challenge is how to make that data useful, how to sift out the most relevant information, analyze it and leverage it as a tool for business success.
The success and profitability of credit card programs is closely tied to how well a CU takes advantage of the available data through data analytics. The combination of analytics and data-driven decisions is a proven success strategy, guiding decisions about marketing, risk and underwriting.
Analytics that address the right data, take advantage of interpretative tools and apply highly accurate assessment can make a huge difference to a credit card program. Guesswork is replaced by guidance based on proven empirical performance, paving the way for a credit union to turn its card program into its highest-performing asset.
This is often done through a "scorecard" that is the end product of all this analysis. It represents the actionable information a credit union needs to move forward on launching, expanding, or streamlining its card program.
A Decision-Making Tool
As a decision-making tool, it essentially distinguishes desirable targets from undesirable ones by predicting rates of acceptance, return, and profitability for the target population.
A scorecard is developed through data analysis that looks at a representative sample of the specific target population and evaluates characteristics and variables about the individuals in that population. With this information, a CU can predict an outcome with accuracy, whether it is the rate of acceptance of a credit card solicitation, the effect of certain interest rate tiers, the short- or long-term profitability of a range of cardholder members, or other activities. There are four main ways a scorecard is used:
* Cardholder acquisition, also known as asset origination. The scorecard indicates which individuals in the target population represent the best and most profitable opportunities for solicitation; not only who has the greatest revenue potential, but who is most likely to respond positively to a solicitation.
* Ongoing account management. Models created through the data analysis can guide the CU in deciding what types of offers (such as credit line increases or balance consolidation offers) to extend to various members that will generate the most loyalty and the greatest use of the card.
* Collections. A scorecard can help deetermine optimal allocation of resources within a department and determine how best to work with and make offers to certain members.
* Recovery. Scorecard analytics can be used to determine which debts to keep and continue to collect, or which to sell off.
Risk Profile Revealed
Effective data analysis also enables an accurate assessment of the risk profile of prospective and current cardholders. By targeting the right people within the relevant profile, loss rates are reduced and it becomes easier to manage losses to desired levels, with appropriate pricing based on risk level.
For a credit union with an existing card portfolio, vintage analysis paired with existing scorecards provides a solid foundation on which to build. As a new group of accounts is added to the credit union's cardholder base, these accounts are tracked in a distinct grouping, or vintage, for performance against historical benchmarks.
The vintage will be compared with scorecards from other vintages and with the larger base of historic data. This process allows and encourages strategy changes relative to how the scorecards are used.
All this requires a continual assessment and reassessment of the data pool. For every new vintage, every new promotional offer, the accuracy of the scorecards needs to be recalculated, with all the new data incorporated. On an ongoing basis, performance of the scorecards-especially in terms of their predictive value-must be critically assessed, tested, and analyzed. If not, it is very easy for scorecard effectiveness to degrade rapidly.
The ideal approach to this kind of data analysis is to magnify the view into account-level profitability, because the greater the level of granularity, the better a CU can determine what is working best in its portfolio and make informed decisions. By being able to identify and flexibly segment the portfolio composition, determine when an account vintage will turn profitable, develop pro formas, drill down to the essential drivers of profitability, and view loss reserves, credit unions can be confident their strategies will work and they can better serve their members.
Alfred Furth is Vice President of Portfolio Analytics and Risk at Capital Services, Sioux Falls, S.D., a payment portfolio management and servicing company. Mr. Furth can be reached at firstname.lastname@example.org.