Crowdsourcing: The next big thing in fraud detection?

Harnessing the power of crowdsourcing is a fresh idea proposed to supplement tried-and-true methods of identifying health insurance fraud.

Crowdsourcing is "the practice of obtaining needed services, ideas, or content by soliciting contributions from a large group of people and especially from the online community rather than from traditional employees or suppliers." Crowdsourcing combines the efforts of many people taking initiative to solve small pieces of a larger puzzle. Crowdsourcing is all about power in numbers.

From a fraud fighting standpoint, the time may be ripe for crowdsourcing since health insurance programs keep losing money despite the government's record-setting fraud recoveries, The Incidental Economist noted. The article touts the value of independent analysis of Medicare payment data that exposed, among other problems, aberrant billings for group psychotherapy.

"If we really wanted to jumpstart fraud detection, we'd give a reward for identifying cases like this," The Incidental Economist noted. Such rewards would align with whistleblower incentives.

One program of this type already exists: The U.S. Department of Health and Human Services offers incentives of up to $1,000 for information leading to fraud-related overpayment recoveries.

On a wider scale, the Centers for Medicare & Medicaid Services partnered with the Harvard-NASA Tournament Lab to leverage crowdsourcing to improve provider screening, according to a Harvard NTL blog post. CMS launched a contest on the TopCoder platform to create a module to standardize enrollment screening per Affordable Care Act requirements and eliminate the need for states to do this work separately.

Seventy-seven participants from 17 countries entered the contest. The result: "A high-quality product, a methodology that worked extremely well, intermediate products that provided great value, built in quality assurance, and a nimble, flexible and cost-effective procurement process," Harvard NTL noted. Full use of the modular product could save about $132,900,000.

For more:
- read The Incidental Economist blog post
- here's the website
- see the Harvard NTL blog post