Autor(es): Sena, Inês ; Silva, Felipe Gustavo Soares da ; Braga, Ana Cristina ; Fernandes, Florbela P. ; Vaz, Clara B. ; Pacheco, Maria F. ; Novais, Paulo ; Lima, José ; Pereira, Ana I.
Data: 2025
Identificador Persistente: http://hdl.handle.net/10198/35214
Origem: Biblioteca Digital do IPB
Assunto(s): Data mining; Machine learning; Occupational accidents; Predictive analysis; Retail sector
Workplace accidents are a global problem impacting companies and society, as employee well-being and productivity/profit can be affected. Portugal ranks fifth among European Union countries despite efforts to reduce their frequency. Predictive solutions have demonstrated promising results in several economic sectors, but the retail sector, the country's third-largest in accident records, remains unexplored. This study proposes a predictive model based on the Multilayer Perceptron (MLP) algorithm to calculate the probability of risk situations occurring in a retail company. Ten databases provided by the company were analyzed and combined into a single dataset using impact scores. The predictive model was developed to predict risk situations in all the company's stores throughout two working days, the current and the next, and the four working shifts. The predictive model was implemented and tested in an integrated system for nine months and achieved 92% accuracy and a 29% precision rate in identifying risk situations. It is concluded that this approach provides a practical solution to assist companies and occupational health and safety teams prevent and minimize workplace accidents, contributing to increased safety and well-being.
