Researchers at the University of Waterloo have developed a tool to help governments and other organisations with limited budgets spend money on building repairs more wisely.

The new tool uses artificial intelligence (AI) and text mining techniques to analyse written inspection reports and determine which work is most urgently needed.

“Those assessments are now largely subjective, the opinions of people based on experience and training. We’re using actual data on buildings to make spending decisions more objective,” University of Waterloo engineering PhD student Kareem Mostafa says.

Researchers looked at inspection reports on the roofs of 400 schools managed by the Toronto District School Board. A computer model was developed to search the one- to two-page reports for about 30 keywords, including words such as ‘damage’ and ‘leaks.’

By analysing the frequency of the keywords, plus factors including the age of roofs, the AI software divided the schools into four categories based on the urgency of repair or replacement. The goal was to give the school board an objective way to target its limited funds, speeding up the assessment process and helping it spend money where it makes the most sense.

“We’re playing Moneyball with building assets,” Kareem adds.

“By using data on buildings instead of opinions, our model also takes potential political headaches out of the process.”

Although the software was developed to assess the need for roof repairs, it can be tweaked to help prioritise other kinds of work for organisations with budget limitations and many buildings to maintain.

Mostafa is also working to incorporate other kinds of data, including AI analysis of photographs, into the assessment model.

A paper on their work, Data mining of school inspection reports to identify the assets with the top renewal priority, appears in the Journal of Building Engineering.