Welcome to the Pondera FraudCast, a weekly blog where we post information on fraud trends, lessons learned from client engagements, and observations from our investigators in the field. We hope you’ll check back often to stay current with our efforts to combat fraud, waste, and abuse in large government programs.
While I don’t think healthcare fraud is a particularly humorous subject, a recent case in Florida does lead to a few chuckles.
Earlier this year, a Northern Florida doctor pled guilty to falsely billing over $1.5 million to Medicare and TRICARE. The billings were submitted for a complex procedure that required the removal of skin and muscle. In reality, most of the procedures actually performed were for routine foot care, including toenail clippings.
So how did this fraudster get caught? It seems the authorities used basic peer comparison analytics to flag suspicious activities. In this doctor’s practice, half of his patients apparently needed the expensive foot procedure, placing him in the top 1% of all providers in the country for this service. This despite the fact that Ocala is only the 45th most populated city in, not even the nation, but the state of Florida with fewer than 60,000 citizens!
The doctor tried to cover his tracks by falsifying patient medical files to make it appear that he had actually performed the procedures, versus simply cutting toenails and performing other routine procedures. He now faces a maximum penalty of 10 years in prison and restitution of $1.5 million.
As the residents of Houston and surrounding areas continue to struggle with the devastation caused by Hurricane Harvey, history shows us that problems will continue long after the homes and businesses have been repaired. Every large natural disaster in this country follows the same pattern: destruction brought on by the disaster, followed by looting and price gouging, followed by huge amounts of fraud committed in the chase for assistance money.
In Texas, all three seem to be occurring at once. We’ve all seen the heartbreaking images and videos of families who have lost everything, unfortunately including those who lost their lives. We’ve also seen the inspiring stories of ordinary people that risk their lives to help a neighbor, a stranger, or a lost family pet.
Now, of course, the looting stories are beginning to circulate. In this case, it appears that law enforcement is doing all that it can to protect life and property, including announcing mandatory jail time for all thieves and burglars. However, the scammers are wasting no time setting up Facebook pages and sending out tweets with links to “relief organizations” that are actually designed to steal money from those who want to help.
I have no doubt that this fraud activity will only increase. Consider these examples following previous disasters:
- Dozens of people were convicted of using fraudulent psychiatric claims following 9/11 to steal up to $50,000 per year in Social Security disability payments.
- A New Jersey man was one of hundreds to receive relief funding (in his case $171,099) after falsely claiming his primary residence was a home damaged by Hurricane Sandy.
- An Alabama woman filed 28 claims for disaster assistance in 5 states following Hurricane Katrina.
Unfortunately, fraud thrives at the intersection of vulnerable populations and large amounts of money. And Hurricane Harvey creates this intersection by displacing so many families, by invoking a government response, and by tapping into the giving spirit of caring Americans.
Even more unfortunate is the fact that most of the fraud will go undetected and unprosecuted. Consider that the vast majority of the 22,000 cases of potential fraud passed to the government's Katrina task force were never prosecuted. And it is likely that FEMA collected less than 5% of the estimated billion dollars of fraud following the Hurricane. Only by increased enforcement and stricter sentencing will we be able to break this heinous pattern. And, to me at least, this is a pattern worth breaking.
It has been an interesting few weeks for the Supplemental Nutrition Assistance Program (SNAP), formerly known as the Food Stamp program, with two high profile busts. Both cases illustrate common schemes used to defraud the SNAP program, which distributed over $70 billion in food-purchasing assistance last year to 44 million Americans.
In Georgia, two convenience store owners used stolen identities to apply for SNAP benefits which were then loaded onto EBT cards (similar to credit cards) and mailed to addresses they controlled. Once received, they swiped the cards at their own convenience stores and pocketed over $800,000 before being caught. The U.S. Attorney assigned to the case said, “They used the SNAP system as an ATM for their personal gain, diverting critical benefits that help those who need assistance in our communities.”
Then, in Delaware, seven case workers at the Department of Health and Social Services were indicted for creating 100 fake accounts and cashing $959,000 in benefits. After creating the accounts, the case workers had the EBT cards mailed to state service centers where they simply intercepted them and used the cards themselves. Their scheme was detected when a supervisor noticed incomplete application data for one of the cards.
The Georgia case illustrates just how easy it can be (at least for a time) to use stolen identities to defraud government programs. Even if the suspects hadn't owned the convenience stores, it would not have been difficult for them to find one that would pay them a discounted price in cash for their cards.
The Delaware case is one we commonly see across states and programs where unscrupulous employees use their knowledge of the system to defraud their own government agency. Large amounts of money, combined with loose supervision, often prove too tempting for those with questionable morals.
A quick check of the government’s fraud reporting website, paymentaccuracy.gov, reveals that improper payment rates for SNAP are still not posted because of reporting problems. I look forward to updated numbers when they are available because even a small number like the 3.2% reported rate for 2014 translates to over $2.2 billion per year in improper payments.
Almost everyone is familiar with antivirus software. Not everyone is familiar with how it works though. Even fewer have examined how we can apply the way antivirus software works to combat fraud. I believe that there are important lessons here which can improve our approach to fraud detection and prevention.
At a high level, antivirus software performs two important functions prior to opening a file on your computer: 1) It compares the file to known viruses and other forms of malware, and 2) It checks the file for suspicious code which may indicate a new, previously unknown virus.
The first function depends on a network of users willing to share known viruses and a system that is able to collect the virus data, design a fix, and disseminate the fix to other users prior to them being infected. The second function depends on heuristic programmers that can design systems to learn and even anticipate potential problems. Working together, this is one of the most effective ways to address the constantly changing nature of Internet malware.
Government fraud prevention, when done properly, works in a very similar manner. By examining known bad actors, bad transactions, and bad behaviors, systems can quickly compare ongoing program data to identify suspect transactions. Modern fraud detection systems also include predictive algorithms that can detect anomalies, trends, patterns, and clusters that may indicate fraud.
Unfortunately, many governments are unable, or unwilling, to share data. This limits the “network” effect that antivirus software uses so effectively. If more states and programs shared fraud schemes and findings, the library of known bad actors and methods could detect fraud and prevent it from moving from state to state and program to program.
The good news is a number of states are moving toward state-wide fraud prevention efforts and a number of government subsidy programs are moving toward cross-state fraud prevention efforts. I am confident that the future success of these efforts will promote additional sharing, leading to a larger network, and more efficient governments.
Big data analytics and the predictive engines they spawned give Internet companies a way to monetize the online experience. By tracing online behavior, companies can target advertising, promotions, and point of sale opportunities based upon past buying decisions. Online habits of Web users can be associated with ideologies, interests, and values. Increasingly sophisticated probability engines predict future buying decisions with enough accuracy to fuel a dramatic increase in online sales and commerce over the past decade. Analysts use temporal versions of these tools to forecast market trends and evaluate risk.
In the fraud detection market however, early attempts to detect fraudulent behaviors using these same probabilistic engines have achieved limited success.
What makes detecting fraud different than detecting interests, values, and ideologies? The simple answer: Fraud is binary in nature–either a particular sequence of behaviors is fraud or it is not. For example, if an individual provider of medical services submits claims to an insurance company for 5,000 hours of services in a week (an instance from actual data), there had better be around 100 employees licensed to provide that service. If there are only three or four employees with the required licenses, the provider has committed fraud. Probabilistic engines struggle to detect fraud because they are not capable of modeling this“all or nothing”nature of violating a law.
At Pondera, we still make use of predictive analytics. But rather than detecting absolute fraud, we use the algorithms mostly to inform our fraud scores and to detect emerging fraud methods.
Once reliable methods of detecting fraud have been developed, predictive engines can also play an important part in helping insurance companies, financial institutions, and government agencies prioritize targets of investigation. Predictive models can identify the highest value targets that will recover the most money or disrupt the largest criminal organizations.