Abstract:

Occupational accidents in the construction industry occur more frequently when compared with other industries. Construction occupational accidents still have not been prevented at the desired level. Several studies in the literature have been conducted to predict the occurrence frequency of these accidents using classical statistical and machine-learning techniques. However, some challenges regarding imbalanced and multicollinearity problems present in the dataset are not considered while analyzing data with a large size and a large number of categorical variables. This study aims to predict the severity of non-fatal construction accidents considering mentioned challenges to obtain more accurate results. In this study, standard binary logistic regression, Firth, Ridge, Lasso, and Elastic Net Regularized logistic regression models were used for the prediction of lost workdays in the construction industry and results were compared. The data used were classified into five groups: victim, workplace, accident time, accident and sequence of events, and post-accident state-related variables. The results showed that Firth’s logistic model is the best-performing model and age, education, vocational education, workplace size, project type, working environment, accident month and year, general and specific activities, material agent, type of injury, and part of body injured are the most significant variables. This study, by providing interpretable machine learning tools, is the first attempt to use proposed models in the area of construction safety in the literature.

Keywords: