Author(s): Sena, Inês ; Mendes, João ; Fernandes, Florbela P. ; Pacheco, Maria F. ; Vaz, Clara B. ; Lima, José ; Braga, A. C. ; Novais, Paulo ; Pereira, Ana I.
Date: 2023
Persistent ID: https://hdl.handle.net/1822/89533
Origin: RepositóriUM - Universidade do Minho
Subject(s): Machine learning algorithms; Occupational accidents; Predictive analytics; Preprocessing techniques
Although different actions to prevent accidents at work have been implemented in companies, the number of accidents at work continues to be a problem for companies and society. In this way, companies have explored alternative solutions that have improved other business factors, such as predictive analysis, an approach that is relatively new when applied to occupational safety. Nevertheless, most reviewed studies focus on the accident dataset, i.e., the casualty’s characteristics, the accidents’ details, and the resulting consequences. This study aims to predict the occurrence of accidents in the following month through different classification algorithms of Machine Learning, namely, Decision Tree, Random Forest, Gradient Boost Model, K-nearest Neighbor, and Naive Bayes, using only organizational information, such as demographic data, absenteeism rates, action plans, and preventive safety actions. Several forecasting models were developed to achieve the best performance and accuracy of the models, based on algorithms with and without the original datasets, balanced for the minority class and balanced considering the majority class. It was concluded that only with some organizational information about the company can it predict the occurrence of accidents in the month ahead.
