An assessment of a workplace is an important event needed to control occupational safety for injuries, incidents prevention, and promotion of a healthy workforce. Global estimation of the burden due to occupational injuries, poor health, worker’s compensation is 4% of GDP or US 2.8 trillion. This study aims to provide insights into occupational injuries using predictive algorithms and predicts days away from work. It will allow business organizations to project operational hours, strategize the occupational safety procedure and reduce injuries. This research focuses on injuries in the healthcare industry in Ohio. Data analytics involves the collection, evaluation of data, and application of predictive algorithms. In this study, multiple supervised machine learning algorithms, such as Decision Tree, Grid Search CV, MLPRegressor, Linear Regression, Ridge, and Lasso, are utilized and compared against each other. The utilized dataset is the historic OSHA data. The pre-processing techniques are: data cleaning and normalization.
Authors: Marina Klaiber, Dr. Bilal Gonen