UMD students in computer science and economics, with a colleague from UCLA, said food service businesses and consumers can monitor and compare practices from outlets across the country.
Ben Bederson, UMD Professor of Computer Science, said the database uses robots to automatically collect data from local government websites, representing a ‘huge leap’ from local and state databases that can miss the big picture and have little impact on compliance actions.
One challenge for the team was developing normalization algorithms to compare data across jurisdictions where it is very different. For some web pages, they had to write custom ‘scrapers’ to get the data, and for others they had to interpret already available databases.
For non-commercial use, the database is publicly available at InspectionRepo.com.
The team has created a regulatory data analytics company, called Hazel Analytics, which produces a commercial grade restaurant inspection database and analytical services for the food service industry.
It is in talks with several national chains and expects to have the first paying customers this year.
They developed analytical tools to compare inspection outcomes across localities and states, and across chain and individual food outlets to improve inspection efficiency and promote retailer compliance, resulting in a decrease in foodborne illnesses, according to Bederson.
“Our data robots cover a large number of local jurisdictions across the US, continuously detecting new data posted by each jurisdiction, and integrating them into a single, standardized, and cumulative database,” he said.