Commercial grain elevators are hazardous agro-manufacturing work environments where workers are prone to serious and life-threatening injuries. The aim of this study is to give insight into safety risks in grain handling facilities through information processing of workers' compensation data on agro-manufacturing occupational incidents within commercial grain elevators in the Midwest region of the United States between 2008 and 2016. The severity of occupational incidents is determined by total dollar amount incurred on medical, indemnity, and other expenses in workers' compensation claims. The most important factors that affect the cost escalation of occupational incidents are extracted using bootstrap partitioning method, and are applied as input for constructing two machine learning models: random forests decision trees, and naïve Bayes. Both models show high accuracy (87.64% and 92.78% respectively) in predicting that a future claim is classified as either low or medium, severity. The models contribute to identifying high injury risk groups, and prevalent incident causes, allowing a more research-based focused intervention effort in grain handling workplaces. In addition, the results are applicable in forecasting cost severity of future claims, and identifying factors that contribute to the escalation of claims costs.
Agro-manufacturing Operations, Machine Learning, Naïve Bayes, Occupational Safety Analytics, Random Forest Decision Trees
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Aviation and Technology
Fatemeh Davoudi Kakhki, Steven A. Freeman, and Gretchen A. Mosher. "Applied machine learning in agro-manufacturing occupational incidents" Procedia Manufacturing (2020): 24-30. https://doi.org/10.1016/j.promfg.2020.05.016