Machine Learning–Based Decision Support Framework for Construction Injury Severity Prediction and Risk Mitigation

Abstract

Construction is a key pillar in the global economy, but it is also an industry that has one of the highest fatality rates. The goal of the current study is to employ machine learning in order to develop a framework based on which better-informed and interpretable injury-risk mitigation decisions can be made for construction sites. Central to the framework, generalizable glass-box and black-box models are developed and validated to predict injury severity levels based on the interdependent effects of identified key injury factors. To demonstrate the framework utility, a data set pertaining to construction site injury cases is utilized. By employing the developed models, safety managers can evaluate different construction site safety risk levels, and the potential high-risk zones can be flagged for devising targeted (i.e., site-specific) proactive risk mitigation strategies. Managers can also use the framework to explore complex relationships between interdependent factors and corresponding cause-and-effect of injury severity, which can further enhance their understanding of the underlying mechanisms that shape construction safety risks. Overall, the current study offers transparent, interpretable and generalizable decision-making insights for safety managers and workplace risk practitioners to better identify, understand, predict, and control the factors influencing construction site injuries and ultimately improve the safety level of their working environments by mitigating the risks of associated project disruptions.