By: Ken Pruett
I thought it might be helpful to give an example of a recent performance monitoring engagement to show just how the performance monitoring process can help. The organization to which I’m referring has been using Knowledge Based Authentication for several years. They are issuing retail credit cards for their online channel. This is an area that usually experiences a higher rate of fraud. The Knowledge Based Authentication product is used prior to credit being issued.
The performance monitoring process involved the organization providing us with a sample of approximately 120,000 records of which some were good and some were bad. Analysis showed that they had a 25 percent referral rate — but they were concerned about the number of frauds they were catching. They felt that too many frauds were getting through; they believed the fraud process was probably too lenient. Based on their input, we started a detailed analytic exercise with the intention, of course, to minimize fraud losses. Our study found that, by changing several criteria items with the set-up, the organization was able to get the tool to be more in-line with expectations. So, by lowering the pass rate by only 9 percent they increased their fraud find rate by 27 percent. This was much more in-line with their goals for this process.
In this situation, a score was being used, in combination with the organization’s customer’s ability to answer questions, to determine the overall accept or refer decision. The change to the current set-up involved requiring customers to answer at least one more question in combination with certain scores. Although the change was minor in nature, it yielded fairly significant results.
Our next step in the engagement involved looking at the questions. Analysis showed that some questions should be eliminated due to poor performance. They were not really separating fraud; so, removing them would be beneficial to the overall process. We also determined that some questions performed very well. We recommended that these questions should carry a higher weight in the overall decision process. An example would be that a customer be required to answer only two questions correct for the higher weighted questions versus three of the lesser performing questions. The key here is to help keep pass rates up while still preventing fraud. Striking this delicate balance is the key objective.
As you can see from this example, this is an ongoing process, but the value in that process is definitely worth the time and effort.