How to prevent procurement fraud
Government agencies must switch from manual fraud defenses to hybrid analytics
By Jon Lemon, Principal Industry Consultant, SAS
The US federal government spends billions each year to conduct mission-critical activities and, in most instances, it does a respectable job. Unfortunately, fraud, waste and abuse is a problem. One area of fraud that is particularly problematic, but is perhaps not as widely considered as benefits or services fraud, is procurement fraud, otherwise thought of as procurement integrity. And it’s time to look at how it can be prevented.
Procurement fraud is perpetrated in several ways, most commonly:
- Contract bid rigging. Several parties compete for a contact – each taking a turn at being the lowest bidder – and the lowest bidder usually wins the contract.
- Grants. An individual makes false statements on a grant application or fails to follow through with the conditions for receiving the grant.
- Travel cards. Federal employees misuse their travel cards for purposes other than travel or in violation of the travel card use requirements.
- Small-acquisition purchase cards. Federal employees can make some purchases on a purchase card, if the expense doesn’t exceed a certain threshold. It’s fraudulent to use that card to break a large purchase into multiple small payments – thus avoiding the bidding process.
- Procurement and acquisitions. This is a “catch-all” category for fraud ranging from kick-backs and pass-thru contracts to large businesses that continue to bid on work they were eligible to compete for as small businesses.
These are all difficult to detect. In theory, there are multiple layers of safeguards built into the government procurement system. The first line of defense is trained and certified contracting officers, their supervisors and compliance officers. The second line is internal auditors who review contracts, conduct periodic audits and employ rudimentary analysis looking for notable deviations from standard practices. And third, each agency has an Inspector General who audits programs and investigates allegations of fraud, waste and abuse.
These defenses have one thing in common: they rely on cumbersome manual processes; inadequate, siloed data; and audits, tips and whistleblowers to uncover the fraud. In other words, it’s discovered it after the fact.
In my experience working proactively with federal agencies, I’ve found identifying complex fraud schemes (and the criminals behind them) is only possible when agencies use a multifaceted, anti-fraud detection approach that combines sophisticated data integration with a hybrid analytical approach. The combination of data integration and a hybrid analytical approach is key to uncovering the crime organizations in the first few months, which greatly limits potential losses to the government and taxpayers.
Integrated analytical applications can help you quickly connect – and reconnect – the information in a variety of ways. Each “strand” of connections represents another way of looking at a fraud event as part of a potentially much larger threat. In this way, applications work together to:
- Stop the pay-and-chase by spotting fraud and error before payment.
- Provide information about threats, trends and risks to support strategic decision making.
- Deliver a complete view of fraudulent behavior.
- Test, simulate and deploy models and rules quickly without dependence on IT.
Criminals take advantage of the government’s inability to connect the dots between state and federal government databases, which contain data about retailers, retail store sales taxes, wage taxes, income tax, corporation records, driver’s licenses, business licenses, criminal records, deportations and more. You must connect that information if you want to spot anomalies and fraud patterns, and recognize malignant social networks BEFORE the fraudster has a chance to strike. The integrity of the procurement process is at risk if government agencies don’t increase their use of hybrid analytics.
A hybrid analytic approach to procurement fraud
Business rules are a good place to start. If bidders show up on a disbarred list, don’t give them a contract. If too many invoices come in on the same day, check them out. Simple enough. However, business rules typically only catch simple schemes and data entry errors.
Analytics changes the game. With the right analytic techniques, you can focus on areas that warrant more scrutiny, without delaying proper transactions.
Anomaly detection looks for behaviors that are unusual or unexpected.
- Historical anomaly detection looks at changes in behavior over time. If the system sees a sudden, drastic shift from historical patterns – with nothing to explain it – this would be flagged and factored into the overall fraud risk score.
- Peer grouping or clustering compares one’s behavior to the norm for a similar peer group and identifies behaviors that are drastically different from what would be expected for that group or type of procurement.
- Profiling defines the typical attributes of good guys and bad guys. When it sees a pattern that matches that of known fraudsters, the system recognizes and flags it accordingly.
- If something is one or two standard deviations from normal, it gets a low risk score and causes no concern. But if a scenario is three, four or 10 times outside the standard deviation of normal, the system will give it a high score and flag it for attention.
Text mining identifies patterns and anomalies from unstructured data, such as reports and social media. For example, if a procurement officer who makes $65,000 a year posts pictures of extravagant purchases on Facebook, you might want to check it out.
With advanced analytics, you can build models that identify attributes or patterns that are highly correlated with known fraud, even for complex and emerging schemes. Analytics answers questions that manual or ad-hoc methods miss. Does this look like the typical habit of bid riggers or those known for counterfeit parts? Does this series of invoices, stair-stepping up and down in dollar value, indicate a vendor trying to find the threshold of scrutiny?
Since much procurement fraud involves collusion, associative linking is invaluable. Link analysis finds relationships among entities based on static attributes (such as phone numbers, addresses or bank accounts) or transactional attributes (business relationships, referrals, etc.). A relationship might be innocuous, but even for valid business you want to be able to show you have done due diligence vetting relationships.
Advantages of this analytical approach
Each technique has a different fit. Rules screen out straightforward cases. Anomaly detection compares what looks normal and unusual. Predictive analysis finds suspicious patterns that would otherwise be hidden. And link analysis points to possible collusion. Independently, each method is very good at detecting a certain type of fraud, but when used in combination, you can see so much more.
These analytical techniques also provide checks and balances for each other. For example, link analysis might reveal a family relationship between parties, but anomaly detection shows the transaction to be normal compared to others of its type. Nothing untoward. This cross-pollination helps reduce false positives, so the system does not generate alerts that consume investigators’ time for no gain.
Ideally, this hybrid approach operates in a loop – called machine learning. What is learned from past fraud (and from suspicious events that proved to be benign) is all fed back into the detection engine to make it ever more accurate and predictive. When the analytics can learn and adapt to change, the system is continuously improving and produces fewer false positives and false negatives over time.
- Download the white paper: Improving Fiscal Responsibility Through Data Analytics.
- For more on fraud from SAS experts, check out the State and Local Connection blog.
Get More Insights
Want more Insights from SAS? Subscribe to our Insights newsletter. Or check back often to get more insights on the topics you care about, including analytics, big data, data management, marketing, and risk & fraud.