Nemesis

Challenges in identifying warranty fraud

By March 26, 2019 No Comments

by David Sachs

The challenges of identifying warranty claim fraud – finding a needle in a haystack?

If you want it to be that way.

Finding warranty claims fraud is as much about us wanting to do something about it as it is about finding the proverbial needle. Not to mention the fact, that we want to avoid the prick from the needle when we find it!

In a survey carried out by the Association of Certified Fraud Examiners sometime back, a typical business loses 5% of revenues each year to fraud. Our world has morphed into one where whenever there is financial or other benefits to be gained with limited risk and acceptable consequences of getting caught there are always some people and organizations who try to take advantage of the opportunity resulting in fraud.

Why is it so difficult?

“Warranty fraud is a serious problem, but not for us”.

For many it is simply the lack of focus, skills and discipline in warranty transactions and analytics. Most organizations have the tools – validation rules, claim process, statistical data analysis — you name it, they seem to be in a good shape, but the devil lies in the details. When you dig a bit deeper, you notice discrepancies and trends you never thought were there.

Is it worth the effort? It is like asking is it worth saving 5% of my revenue. For some, it may not be, for most that is not so true.

Role of the enforcer: For smaller outfits, warranty control is often a part time role and an activity that deserves no more than a check mark on a list of things to do. For larger outfits, high turnover of and limited induction to the validators often leads to a situation where the processes and controls are defined, but not followed properly. Issues with consistency, timeliness and quality of warranty data is yet another big reason why organizations do not see the true benefits of a robust consistent warranty claims fraud tracking system.

Then to make it all worse, with downsizing and cost-cutting, manufacturers are reducing the size of their audit staffs. So people are forced to try to do more with less.

Global perspective: In warranty fraud analytics you need to take a look at the individual claim level, as well as global and regional averages and everything in between. What looks like a valid claim at individual level can appear fraudulent when looked at an aggregate level.

Mild consequences: Often the only consequence of issuing a fraudulent warranty claim is that the claim is rejected. Not even a slap on the hand! This provides an incentive for some people to try fraud, since there is only an upside if the fraud is successful and the worst case scenario is equal to not doing anything.

Bigger Picture: is usually lacking. Individual auditors don’t see the bigger patterns, because this person is looking at a hundred claims, and somebody else is looking at a different hundred claims, and they’re not sharing that knowledge across the broader set of claims. So they can often miss things.”

The solution is to automate the process so that a single system is “reading” all the claims, setting rules for items such as what parts go with which labor codes and looking for unusual patterns in the data.

Different perpetrators, victims, motivations and methods: Fraudsters can include any party in the warranty chain either alone or in collusion with others, typically customers, service agents or warranty providers. Victims of fraud can include any party, typically manufacturers, warranty providers and customers.

The motivations fall broadly into two categories – service cost avoidance (I have a faulty product and want to get it repaired free-of-charge) and revenue increase (claiming and re-selling parts or products, excess charging of existing or non-existing warranty service)

The methods are numerous – new methods are invented as old methods are uncovered and blocked.

What do we do?

Analytics is needed to evaluate claim validity across individual claims. This can be targeted or general. In targeted analytics you know a certain fraudulent pattern and want to verify its existence with a specific customer or service agent. This allows consistency of process and search methodology. It, however, suffers from the “I know what I know” syndrome.

In general analytics you slice and dice the data in different ways, try to identify anomalies and outliers and then understand whether the reason for the anomaly is fraud or something else. This allows you to stay on top of new strategies being used by fraudsters and nipping them in the bud before it does significant damage.

So, how do we harness this new knowledge and help us get smarter?

Outsmarting the opposition – self-learning systems: With more sophisticated analytics methods, you can detect the more complex fraud schemes and even find cases you don’t necessarily know about. Fraudsters are getting more sophisticated. People are getting better at working around systems that have historically been used to find this kind of fraud.

Self-learning solutions or ‘smart’ solutions use a closed loop approach to recirculate new knowledge back into the system of checks and balances and stay on top of emerging strategies to commit warranty fraud.

What the doctor prescribes: Automate your rules-based selection process using text and data based analytic models, look for anomalies across claims, service providers, and networks of service providers, score claims before they are paid, preferably score claims in real time, rank claims and service providers based on likelihood of fraud and indicate type of fraud suspected, and focus auditors on the right claims and service providers.

And voila !

To top it all, all this analyzing and scoring and investigating should be done before the suspect claims are paid, because it’s easier than trying to get the money back!

X