Artificial Intelligence in Human Resource Management: Transforming Employee Engagement and Organizational Performance

Abstract

The use of artificial intelligence is growing rapidly in HRM practices since AI can help analyze workforce dynamics, measure employees' engagement, and predict organizational performance. This current study examines the application of AI-driven HR analytics and its contribution to transforming employee engagement and organizational performance based on an existing employee performance and productivity dataset including 100,000 employee records. In terms of the study design, the research involved a quantitative approach and used exploratory data analysis, correlation analysis, heatmap visualized clustering, principal component analysis, random forest classification, and feature importance analysis to examine the dataset. It has been found out that employee performance levels were fairly balanced among the sample size, while engagement levels indicated medium and even distribution according to employee satisfaction scores. As for the correlation analysis, a positive relationship has been identified between performance score and monthly salary, which was recognized as leakage prone data and therefore removed from the prediction model to preserve scientific integrity. The resulting random forest model indicates that predicting organizational performance without the use of salary-related data is quite complicated, suggesting that workforce behavior is multi-dimensional and can be described in numerous ways. The main predictors in terms of their importance include employee satisfaction score, number of training hours, projects managed, employee's age, weekly work hours, and overtime hours worked. It has been concluded that employee engagement, workforce development activities, and workload-related variables play a crucial role in AI-powered HRM practices.