The Communications Fraud Control Association (CFCA) estimated annual telecom fraud losses at $54 billion to $60 billion in 2006. Today, the losses continue to be substantial, and while many types of fraud have been identified, the most prevalent by far is subscription fraud.

A new subscriber signs up for mobile service using false or stolen identification, with no intention of paying the bill. Since new subscribers are given a grace period of one to three months before the account is shut off, the criminal can make thousands of dollars worth of calls before being detected.

Different solutions have been tried without success. A common method was to look for patterns of use that suggest potential fraud. Criminals adapted and learned to probe the limits of these fraud detection systems fairly quickly.

Enough is known about telecom fraudsters to spot them when they subscribe. Similarity searching technology vets subscribers against lists of known bad actors. Using multiple public and private data sources, non-obvious relationships highlight risky individuals, and they are asked to submit to a more thorough qualification process.

Identity Resolution is already used across multiple industries to solve similar problems. By matching an individual’s attributes with common attributes associated with those committing fraud, the “bad guys” are being detected in areas like lottery fraud, fusions centers, insider trading, and workers’ compensation fraud.