Identity verification, analytics can help agencies fight fraud

Fraudsters have been setting up schemes on government programs essentially since the programs were created. In a sense, if there is money to be had, criminals will try to get their hands on it – many of them will go to great lengths to do so.

That said, it’s no surprise that COVID-19 has created an environment particularly ripe for fraudulent activity. When the pandemic hit in early 2020, government unemployment offices were inundated with legitimate claims as well as scams looking to take advantage of the system and the chaos caused by the flood of claims.

Indeed, as of December 2020, almost 68% of the entire working population in the country had filed unemployment insurance claims; however, the actual number of unemployed was just under 10%, according to the Bureau of Labor Statistics. At least five states had more unemployment insurance claims than the entire pool of civilian workers residing in that state at the start of 2020, and the US Department of Labor reported that at least 10% of the $872 billion of Pandemic Unemployment Benefits (as of September 30, 2021) was paid improperly, likely as a result of fraud.

Access to new technologies such as bots and artificial intelligence has given criminals, both those acting individually and large organized crime syndicates, the power to submit fraudulent benefit claims on a massive scale.

First, fraudsters purchase stolen IDs, many of which are purchased on the dark web, or create synthetic (or “Frankenstein”) IDs by combining various pieces of identity data from different sources. Then they use bots to completely flood government systems and swipe fraudulent apps, which often go unnoticed among the flood of legitimate apps.

Many organized criminal networks use underpaid workers from overseas to enter data into application portals for unemployment insurance and other related programs. They solve captchas or find email addresses and match zip codes to move the wheels of the system.

As the government attempts to limit criminal activity, many agencies are scrambling to deploy technology solutions that allow them to detect anomalies and detect fraud in programs such as Unemployment Insurance, Medicare/Medicaid and even the supplementary nutritional assistance program.

Automated identity verification

With nearly 30% of fraudulent unemployment insurance claims in major states based on stolen Social Security numbers, it’s much harder for government agencies to spot anomalies. Implementing an Automated Identity Verification (AIV) system can be a lifesaver for agency IT teams that are understaffed and overworked for several reasons:

  • Improved processing time – By automating identity verification, government agencies can process more requests quickly. Using real-time credit data can help weed out fraudulent claims before they enter the system. Faster processing also contributes to a higher user satisfaction rate among legitimate applicants who receive more efficient processing.
  • Reduced Human Error – AIV eliminates the potential for human error common when staff feel the stress of doing more with less. Even with well-trained and experienced employees in place, errors, omissions and misunderstandings can overlook fraudulent claims.
  • Cheaper than deploying new workers – The growing demand for skilled IT professionals makes these positions very competitive and often prohibitively expensive for agencies with a set annual budget.
  • Scalability – Even government IT shops that can find, hire, and train new skilled employees still face seasonal (quarter-end, year-end) or event-based (disaster, pandemic) scalability challenges who are testing their normal daily workload. AIV can offer flexibility during peak periods.

When automated identity verification is properly implemented, government entities can better understand and clarify complaints needing investigation, saving valuable time and resources often spent investigating perfectly legitimate complaints. .

Data analysis for fraud detection and prevention

Banks, hospitals, educational institutions, and manufacturing companies have been using data analytics, artificial intelligence, and machine learning to help detect fraud for several years now. Both internal IT and external contractors have found it to be a valuable analytical tool for detecting fraud, monitoring transactions, and ensuring employee and customer compliance.

A 2020 report commissioned by researchers from the United States Administrative Conference found that federal agencies were closing the gap and that 45% of 142 agencies surveyed were also using AI and/or machine learning to help fraud analysis in two key areas:

1. Use data analytics to detect and diagnose fraud after the fact.

Data analytics can help complement IT and financial audit teams and improve the overall efficiency and effectiveness of their post-mortem audits. Analytics allow data from disparate systems to be compared quickly and efficiently, more confidently identifying anomalies between them.

These data mining and data matching techniques can produce reports that detect potentially false, inflated, or duplicate invoices or payments and can identify fraud or improper payments that have already been granted. This allows agencies to identify bad actors, recover funds faster, and identify and eliminate fraud, waste, and abuse in the future.

2. Implement behavioral analytics to prevent fraud.

As important as detecting, pursuing and recovering from fraud is, using behavioral analytics to help prevent fraudulent activity by verifying identity before a claim is paid is the real opportunity. The US Department of Labor reported that in 2020, a person used a single Social Security number to file for unemployment in 40 different states, 29 of which paid. Deploying preventive behavioral analysis technology can detect these types of anomalies and discrepancies before fraudsters receive their money.

AI-based cross-matching or pattern and cluster recognition algorithms can compare well-established facts and behavioral patterns of all aspects of a typical transaction and then compare them to what is actually being submitted. For example, while it typically takes users about six to eight minutes to complete an online UI application, applications that arrive in less than a minute should be flagged as suspicious and investigated. because they are probably produced by a bot.

Manual verification tends to focus on the validity/truthfulness of submitted data and may overlook other anomalies. Since analytical monitoring software can be run 24/7, it can help detect when an account has been compromised. Identifying an unusual set of login patterns — multiple times a day, from an odd IP address, or at times that wouldn’t normally match the user’s time zone — can send up red flags.

As early as 2018, the Government Accountability Office and industry groups such as the Association of Certified Fraud Examiners published a report that risk assessment programs using proactive data analysis reduced fraud losses by more than 50%. %.

Now is the time to upgrade anti-fraud systems

As we head into 2022, governments need to implement modern technologies that fight fraud. Agencies are just regaining their strength and capacity after adapting to the demands of the pandemic, and expectations have never been higher. The combination of an automated verification system and data analytics for prevention and detection helps create a powerful tool for today’s government IT professionals who are experiencing a sea change in the volume and how the fraud is perpetrated.

Criminals will always try to steal well-funded government programs, but it’s a fight we can’t afford to lose. Implementing these technologies can bring deeper and more lasting changes to the overall fraud landscape. Armed with hard data to illustrate potential risks to affected benefit programs, IT-savvy government leaders can provide documents to request additional resources, funding, and even policy changes.

Comments are closed.