Safety councils are nothing new for the construction industry, but not many of them can say they include the biggest names in the industry and champion some of the most cutting-edge technology available for preventing jobsite accidents.
The Predictive Analytics Strategic Council, founded earlier this year, encompasses some of the largest players in commercial construction, including Skanska, Suffolk and DPR.
Membership is about more than just showing up to meetings; council members must bring proprietary data to the table, sharing historical digital project data from a period of more than 10 years.
The council uses this collective data to build artificial intelligence-based predictive models for safety and risk that will be used by member firms and others in the industry.
Predictive Analytics Strategic Council members
|JE Dunn Construction|
|Shawmut Design and Construction|
The shared data ranges from location, size and dollar value of the project to the schedule duration and incident information about a completed job. In the future, council members are considering studying even more factors such as manpower, requests for information (RFIs) and work hours, which may or may not determine safety outcomes, according to council member Marni Hogen, director of health and safety at Mortenson.
For instance, one working theory is that quick turnaround on RFIs means contractors have access to up-to-date answers, leading to less chance of rework and the ability to stay on schedule, which plays a big part in reducing safety incidents, she said.
In addition, the industry’s massive shortage of skilled labor has made understanding safety data more important than ever, Hogen said, so the council is considering incorporating data about the training and tenure of workers on each site.
Predictive analytics allows construction companies to look at leading safety indicators instead of relying solely on meeting compliance standards, said safety consultant Carl Heinlein, a director-at-large on the American Society of Safety Professionals' board of directors.
Though the analysis uses historical data, the goal is to look at what's coming around the corner. "It's about being forward-thinking instead of looking backward," he said, adding that the data collected by the council will increase safety and help prevent jobsite incidents because it heralds a statistical look at trends that involve preventable factors.
In addition, by working together, member companies are able to identify trends they might not have otherwise seen just working alone, said Jit Kee Chin, the council's chairperson and Suffolk's executive vice president and chief data officer.
"No one company has quite the volume of data it takes to create really good artificial intelligence," she said. "The council provides a way to get together to explore some of the potential that advanced analytics has to offer."
The council relies on the AI-based system from image-analysis firm Smartvid.io, dubbed "Vinnie," that aggregates information from each of the firms to help predict future incidents and hazards.
The group is building on the results of a Smartvid.io and Suffolk study showing that Vinnie learned from Suffolk's data to predict roughly one in five safety incidents with 81% accuracy.
The five new companies that joined this fall — Skanska USA, Skanska Sweden, Webcor Builders, Obayashi and Lithko Contracting — will bring more data to the ultimate goal of increasing worker safety, according to Hogen.
“It’s exciting because the more information we have, the better our insight will be,” she said.
The drive to ensure construction sites are as accident-free as possible fuels members' commitment to collaborate, said Josh Kanner, CEO of Smartvid.io and technical chair of the council.
“Safety brings everyone together for a great end goal and also has additional benefits to each member as it helps them start to get a handle on their operational data as well as start to see what potential it has for safety and beyond,” he said.