How to Fraud Optimize
In the recent post “ROI on Authentication and Identification,” we discussed the topic of tackling fraud losses and turning the tide on fraud prevention as a “cost center.” At the end of the article, we promised we would take a look at the tactical makeup of a fraud profit optimization point. Calculating the POP is about understanding the drivers around fraud ROI. The first step is to understand costs and revenue. We recommend first understanding the following three higher level costs.
- Average cost to automate detection of identity fraud (e.g. third party vendor costs, ongoing systems processing, etc.)
- Average cost per manual review (e.g. staffing levels needed, vendor product costs, etc.)
- Average lost opportunity cost for abandoned transactions. A process that is too laborious or slow can result in increased abandonment of good customers – and lost revenue opportunities, which should also be treated as a cost.
These three will serve as the bottom line dollar drivers. Each one of these drivers is considered against the various likelihood of their use. Checking every credit request with invasive KBA increases all three costs and brings your business to a standstill. Not using any KBA reduces all three costs but drives the fraud loss (that parent number) through the roof. These costs all scale based on certain levers that also have to be factored in. The five relevant to this discussion are:
- Percentage of transactions that passed automatically and later turn out to be bad due to identity fraud as well as the percentage that passed automatically that turn out to be good. This is essentially an indication of how good your fraud model is. If you don’t have a fraud model, then all transactions pass automatically through to your credit risk policy.
- Percentage of transactions stopped for manual review. This will be the lever on your average cost per manual review.
- Percentage of transactions manually reviewed that are approved and turn out to be good. This will be your false-positive rate and a good KPI on your fraud segmentation strategy.
- Rate of manual review abandonment. This is the number of customers unwilling to answer KBA questions. Some of this is fraud, and some of this is impatient, high value customers.
- Average revenue amount to each successfully booked transaction that does not turn out to be a loss due to identity fraud. This is your top line revenue used as the counter-balance to your overall fraud cost.
With these five quantified, you can now determine the current POP for your business and assess how improvements can affect the POP in positive ways. We will walk through this in our CBA post.
According to Equifax case studies, it is possible to achieve the capture of 70 percent of the identity frauds, while only stopping 10 percent of the entire population for manual review. This means that 90 percent of the transactions are automatically approved and passed through with no manual intervention needed. This alone is a tremendous workflow savings, not to mention the losses saved due to the boost in the fraud capture rate. In our final article on ROI, we will go ahead and put these numbers into a cost benefit analysis structure and make up some numbers to help visualize the process.
Recommended For You
The CERCA Spring Conference, held on May 16, capped a broadly successful 2018 filing season that saw tax identity theft reduced by […]
Fraudulent account activity and identity fraud are both significant drains to today’s business resources. In the era of online and mobile commerce, […]
Fraudsters are a smart group. With each fraud prevention method that’s introduced, they figure out ways to work around it. […]
The growth of synthetic identity fraud shows few signs of slowing. Data breaches, social media mining, phishing and other schemes have given […]