Abstract
Contemporary organizations need effective manpower management systems that ensure productivity, transparency, and data-driven decision-making. Conventional HR management practices involve manual encoding, disorganized spreadsheets, and unconnected monitoring systems that result in inaccurate attendance tracking, late performance appraisals, and inefficient compensation calculations. Such conventional practices decrease organizational efficiency and make it difficult to plan for strategic HR management. The research design adopted in the study was a mixed-methods approach, which involved the use of quantitative system performance analysis and qualitative user feedback. The analysis was conducted on HR staff, departmental supervisors, and employees in the selected organizations that implemented the HireUps system. Quantitative data was collected using system analytics, which included attendance accuracy, payroll processing time, performance analysis turnaround, and Machine Learning prediction accuracy. The qualitative data was collected using surveys and interviews to gather information on usability, reliability, transparency, and user satisfaction. Sixty HR personnel, supervisors, and employees evaluated the HireUps system. At a stated confidence level of 95%, attendance monitoring achieved 97.8% accuracy, payroll and compensation processing time improved by 40%, and 95.6% of respondents provided positive feedback on the transparency, clarity, and accessibility of performance assessment. The reported attendance, processing-time, and user-feedback results suggest operational benefits for HR administration. However, the machine-learning component requires separate validation, including the prediction target, dataset, algorithm, test procedure, and performance measures. The basis for the stated confidence level should also be provided.
