Case-based reasoning approach for assessing safety performance using safety-related measures

Although the use of safety-related measures (SRM) has been advocated in the literature, construction companies often rely on reactive indicators instead of SRM to evaluate safety performance. A challenge with using SRM in practice arises when faced with the uniqueness of construction organizations. Distinctive practices and cultures affect the availability and quantity of data, which in turn limits the reliability of conventional SRM-based evaluation methods. This study proposes a case-based reasoning (CBR) approach that makes efficient use of existing SRM available within an organization to reliably evaluate safety performance. The model was validated using statistical tests to compare model output with actual performance. To test model applicability, we conducted a case study: based on information available in an industrial construction organization, including schedule performance and payroll data, 27 measures were identified. The results demonstrated that the proposed approach is able to evaluate safety performance trends in consideration of unique organizational characteristics using SRM. We expect that the model approach and results will support managers in tailoring safety goals and programs to particular contexts.