Analytics Predictive for HRM: Using Machine Learning to Improve Workforce Scheduling and Staff Engagement

Human resource management relies heavily on staff engagement in the workplace and workforce scheduling. Increased performance and results are ultimately the result of engaged and enthusiastic employees who feel a feeling of devotion, loyalty, and connection to their company. Workforce scheduling and staff engagement are influenced by various organizational elements, but little is known about the specific elements that influence them. This paper discusses improving workforce scheduling and staff engagement using data-driven methodologies and machine-learning techniques such as random forests, gradient boosting, artificial neural networks (ANN), and additional trees. The study-generated framework depends on historical statistics from the Public Utility Service Billing Organization. The ANN simulated framework, with its feature collection and carefully selected training variables, shows how useful the framework can be as a decision support tool for workforce scheduling in production and service operations. The below variables are employed as organizational elements in the prediction framework and feature significance evaluation, with staff engagement serving as the resulting aspect: equal treatment, diversity, and participation; secure culture; wellness and health; direct managers; quality of evaluations; care quality; harassment and discrimination; assault; and teamwork. In terms of prediction accuracy, all of the techniques yield outcomes that are similar in terms of prediction accuracy and feature significance order. According to the findings, teamwork is the second most important element influencing employee engagement, after secure culture.