Thanks to a collaboration between the University of Arizona and tech startup Discern Science International Inc., technology capable of detecting deception may soon be available to a number of industries, for a variety of purposes.

Originally developed to detect deception of travelers at the U.S.-Mexico border, the technology, called AVATAR (or Automated Virtual Agent for Truth Assessments in Real-Time), poses questions to users via an interactive electronic interviewer. As the user responds, the system records details such as facial expressions in high-definition video while sensors measure and record other data, such as signals from the user’s voice, eyes and body.

That information passes through an analytical algorithm where the data generates nearly instant color-coded outcomes. For instance, green means that the user can pass while yellow requires additional analysis and red signals considerable issues, requiring deeper investigation.

“The AVATAR technology was developed for the most rigorous and difficult task of detecting deception at the border,” said Jay Nunamaker, director of the UA Center for the Management of Information. “It had to allow innocent people to quickly pass through the border, while simultaneously identifying those attempting deception — and do it all in about 30 seconds.”

In the past, the system was 70% to 90% accurate — an improvement over humans who catch instances of deception only 54% of the time. Yet, that 70% to 90% range is expected to improve with time.

“We have designed studies to accelerate the AVATAR’s learning by engaging people who will be well compensated if they can fool the AVATAR,” said Nunamaker.

Discern Science International Inc. intends to use the technology for applications beyond border security with plans to commercialize it over many different fields.