Application of Machine Learning in the Prediction of Employee Satisfaction with Support Provided in a National Park

Employee satisfaction with support provided after an occupational injury in national parks has an impact on both the employee and the organisation. Machine learning (ML) classification provides techniques that can be useful in predicting employee satisfaction with the support provided after an occupational injury. The main objective of this study was to develop a model that can predict employee satisfaction with the support provided after an occupational injury in the Kruger National Park. The data were collected from 241 employees who experienced an occupational injury between 2006 and 2016 in the Kruger National Park in South Africa. Features used as inputs to the machine learning algorithm included employee characteristics such as job title, years of experience, salary, and performance evaluation. Finally, the nature of work, workload, job satisfaction, company culture, and opportunities for growth and development were also considered. The Support Vector Machines (SVM), k-Nearest Neighbours (k-NN), XGB Classifier, and the Deep Learning Neural Network (DNN) had a good performance in predicting employee satisfaction with the support provided. The k-NN, using training data with Random oversampling, had the highest overall accuracy of 71%. The model predicted employees who did not have adequate employee satisfaction with the support provided with a precision of 72%, a recall of 80%, and an f1-score of 76%. The XGB classifier with an f-score of 69% and the XGB classifier using data with random oversampling with an f1-score of 69% had the highest accuracy in predicting whether employees were adequately satisfied with the support provided. Discussion and conclusion: The findings suggest that both the XGB classifier without oversampling and the XGB classifier with oversampling techniques perform equally well in predicting whether employees are satisfied with the support provided. Therefore, management at the Kruger National Park can use these predictions to focus their interventions on the support provided to employees after an occupational injury to enhance employee satisfaction.