The machine learning tactics behind PavCon's predictive models for the Air Force

With petabytes of sensitive information in its possession, strategy and engineering firm PavCon LLC uses Amazon Web Services Inc. to keep its data secure as a U.S. Air Force contractor. The company also uses that information to improve its current systems and leveraging machine learning and artificial intelligence to predict potential threats and upcoming maintenance.

“A lot of the data in the Air Force is human entry, so it’s manual, which means it’s open and rife for a lot of error into that data. So we’re focused heavily on the data integrity,” said Milissa Pavlik (pictured), president and chief executive officer at PavCon LLC. “What we’ve done is we’ve looked at those supervised and unsupervised [machine learning] models, we’ve taken a whole different approach to infuse it with domain expertise.”

Pavlik spoke with John Furrier, host of theCUBE, SiliconANGLE Media’s livestreaming studio, during the AWS Summit Washington, DC event. They discussed using machine learning to assist the Air Force, modernizing the Air Force with predictive maintenance models and more. (*Disclosure below.)

Soaring into the cloud

With the power of machine learning, PavCon was able to lessen the amount of time spent monitoring data, freeing up resources for tasks such as predictive maintenance, which analyzes the condition of hardware to determine when maintenance is necessary.

“In this case, we’re talking about focusing on those top drivers, and depending on the type of data that we had, it helps us dictate on supervised versus supervised and going the unsupervised route,” Pavlik said. She continued that although some scenarios still call for supervision, with more automation and more automated data collection, unsupervised will be the way to go.

When it came to adapting for today’s digital economy while protecting valuable information, PavCon entrusted AWS handle sensitive information, tapping its massive, scalable infrastructure.

“When we started down this path and we had to identify quickly a format and a host location that would allow us not only handle large amounts of data but do all of the deep analysis we needed to AWS GovCloud is where that came in,” Pavlik said. “They have some great native services that are inside their cloud as well as the pairing and easy collaboration among not only licensed products but also all that free and open-source that’s out there.”

Watch the complete video interview below, and be sure to check out more of SiliconANGLE’s and theCUBE’s coverage of the AWS Summit Washington, DC event. (* Disclosure: TheCUBE is a paid media partner for AWS Summit Washington, DC. Neither Amazon Web Services Inc., the sponsor for theCUBE’s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE