Abstract
BackgroundEmployee health is an essential issue for Human Resource Management (HRM). The employees' health level is undeniably correlated to the job position in which they work since it may harm their well-being, and they may not be capable of performing their duties properly. Prompt diagnosis and resolution of employees' physical complications are highly critical.MethodsMachine learning (ML) is the state-of-the-art method potentially utilized to make early predictions to safeguard employees' healthiness. The technical laborers within the food manufacturing company are included in this Research. The functional classification models, namely, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Logistic Regression (LR), Decision Tree, are exploited to predict the employees' wellness for their vocation. K-fold Cross-Validation (KCV) and Confusion Matrix were applied in this study, the former for estimating the model's functionality and the latter for forecasting accuracy.ResultsAfter implementing four models on the 231 employees, the accuracy was extracted out, SVM with 78%, KNN with 78%, Decision Tree with 80%, and the highest for LR algorithm with 84%.ConclusionsIn this Research, the LR algorithm was opted to paving the way for Human Resources Managers in order to utilize a functional system to predict the Suitability of factory workers concerning their healthiness. The Hearing condition was picked out as a leading factor in selecting employees for their job position. Consequently, it is significant to planning a hearing conservation program for employees, especially those exposed to excessive noise.Trial Registration: Retrospectively registered.