Why aren't insurers using analytics to fight fraud?
Five excuses - and the cost of not connecting the dots
Many insurance companies are now looking to technology to help identify suspicious claims. Suspicious claims not only involve what is being claimed, but also who is making the claim and when and how the claim is made. The goal is to identify patterns and assess commonalities with other seemingly unrelated cases – subtle similarities that might escape even the most seasoned adjuster.
These subtle connections are often the Achilles heel of crime-ring-based fraud: There are only so many degrees of separation existing between all of the participants. This is where monitoring people's social networks can be helpful. For example, individuals with similar-sounding names frequent certain repair garages; maybe this ties in with a small network of household addresses combined with a cell phone number that pops up several times – once as that of the driver in an accident and the next time, under a slightly different name, as that of a witness. Social network analysis helps uncover these previously unseen links.
Integrating social network analysis tools into a broader fraud framework guides adjusters and optimizes efforts to detect fraudulent claims. By using a framework with a comprehensive fraud scoring engine that incorporates a combination of different analytical techniques – automated business rules, database searches, anomaly and exception reporting, predictive modeling, text mining and network link analysis – adjusters are able to determine the likelihood a claim is fraudulent and prioritize their efforts accordingly.
Here are the top five excuses for not using predictive analytics for insurance fraud detection – and why they're wrong.
Excuse No.1 - We don't have enough data
Predictive modeling for insurance fraud detection involves analyzing an existing set of known suspicious claims in order to build a set of predictive indicators that can be used to identify similar suspicious claims in the future.
This technique is powerful, but requires a large set of known suspicious claims on which to build a model. If companies have only a small set of known suspicious claim history data, they often believe they can't successfully employ a technology-assisted fraud detection program.
Reality: A number of statistical approaches can be used to build a solid predictive analytic solution, even if few suspicious claims have been identified in the past. For example, a hybrid solution combining business rules, anomaly detection and social network analysis can identify suspicious claims even if no suspicious claim history is provided.
Excuse No. 2 - We don't have good data
Overworked adjusters and claim processors have a tendency to take the path of least resistance in order to meet their objectives. Have you ever discovered a claimant with the Social Security Number 999-999-9999 or an address of "Unknown" in your claim system? Data quality issues are a reality for any large organization. Many analysts and investigators have been frustrated by poor-quality data in transactional systems.
Reality: Data quality issues do not preclude a successful technology implementation. A robust insurance fraud detection solution incorporates data preparation that carefully cleanses data to remove problems. However, be careful not to clean too deeply. Improper data cleansing techniques can actually harm the data set by erroneously categorizing anomalies due to fraud as data quality errors to be removed.
Excuse No. 3 - Our data is too fragmented
Information silos are prevalent in the insurance industry. Business units are beginning to see the value of sharing data across the enterprise, but many organizations house and manage their own data. Given the fact that most companies use a patchwork of transactional systems for ratings, customer service, policy administration, claims administration, payment processing and human resources, it's no wonder that their data is fragmented. With all of this information located in different places, fraud detection projects are often shelved because they are perceived as too complex.
Reality: It is not necessary to revise the entire corporate information technology infrastructure to build a fraud detection solution. Enterprise solution vendors can use data integration tools to incorporate key data elements from various internal systems. By combining information from these disparate information sources, new insights and fraud detection capabilities are immediately possible.
Excuse No. 4 - It's all in the notes
Studies suggest that 80 percent of insurer data is unstructured text. Any insurance investigator will tell you that the most valuable information about a claim is not in the discrete structured data fields – it's in the notes. It's impractical to have a unique field for every piece of useful information; as a result, the claim notes text field becomes a rich information source. Unfortunately, text fields are not typically used for reporting, and therefore are not available in data warehouses. As such, they're not considered a viable data source for a predictive model.
Reality: Text analytics can be one of the most powerful components of fraud detection. Any seasoned investigator wants to read the vital information in the insurance claim notes. Therefore predictive models should make use of this valuable unstructured data. In some fraud detection solutions, up to half of the data elements used in a predictive analytics come from unstructured data sources.
Excuse No. 5 - We can't handle any more cases
Insurance investigators often have limited budgets and have to maximize their scarce resources. Most of them already have more work than they can handle. When asked about a predictive analytics solution to identify suspicious claims for further investigation, some organizations say, "No thanks – we're already swamped."
Reality: Yes, fraud technology solutions can help organizations identify more cases to investigate, but a critical, often overlooked benefit is the ability to prioritize work more effectively. Most organizations operate on a first-come, first-served basis and simply work on the cases as they come in. Business rules, reporting tools and case management systems can help directors better manage their scarce investigative resources. Even if the company is investigating the same number of cases, an investigator can dramatically improve productivity and impact by effectively prioritizing caseloads.
The bottom line
The bottom line is this: Given the increase in fraudulent claims, it is imperative for insurance companies to employ technology to combat crime-ring-based fraud. Organized fraud is, by its very nature, active, methodical and extremely agile. By using both structured and unstructured data, firms will be able to determine the likelihood that a claim is fraudulent, prioritize their efforts and reduce their claims expenses significantly.
Bio: James Ruotolo is Principal for Insurance Fraud Solutions, Global Fraud and Financial Crimes Practice at SAS.
G. Wesley Gill is Executive Lead and Head of Governance, Enterprise Risk and Compliance at SAS. Wes.Gill@sas.com
Staying ahead of fraud with analytics
At SAS Global Forum 2011, an expert panel with representatives from Los Angeles County and the National Insurance Crime Bureau shared how they use analytics to fight fraud. Here are the common themes that emerged:
- The need for an automated approach.
- It's all about getting the data together – and finding new opportunities in the data.
- Culture change is a critical success factor.