By: iPadfanzz staff on March 19, 2013
Sift Science, the startup founded by former Google engineers, says it is opening up the testing of its fraud-detection service for e-commerce and other sites to the public and has $5.5 million in funding from some heavy-hitter investors to back its play. The company claims that the system is designed to adapt to the ever-changing techniques used by criminals online and can easily find out fraudsters before they do harm.
“Many anti-fraud technologies follow a set number, maybe 175 to 225 rules, against which to measure user behavior — the problem is fraudsters don’t follow the rules and change all the time,” Sift Science co-founder Brandon Ballinger said in a recent interview.
“We take a machine learning approach to learn from patterns early as they form to predict whether a new user is fraudulent,” he said. Sift Science’s machine learning algorithm has automatically learned one million patterns that predict fraud, and as more sites join the network, it will learn more patterns to help everybody fight fraud more accurately, he said.
Sift Science had previously raised $1.5 million in seed funding, bringing its total raise to $5.5 million.
The service is largely meant for online marketplaces, payment networks, and e-commerce sites, where there are more chances of a fraud. Businesses can integrate Sift Science’s technology by copying and pasting a small snippet of Javascript code to their sites, the company says.
Ballinger says the system has been designed a team of expert engineers – eight of the company’s 9 employees are engineers and 5 are ex-Google engineers. “We’re taking the Google approach of large-scale machine learning,” he said.
Sift Science competes against the likes of fraud detection services including Silver Tail Systems, which EMC bought last year and which watches and tracks user navigation trends; and Threatmetrix, which watches device IDs.
