Advisers

Sheryl F. Adovas

Discipline

Information systems

Abstract

Employee turnover remains a major challenge in the travel and tours sector, causing operational disruptions, increased recruitment and training costs, and declining service quality. Many organizations still rely on manual human resource processes and lack predictive tools to identify employees at risk of resignation. To address this gap, this study developed a Human Resource Management System (HRMS) integrated with an AI-based attrition risk monitoring module using Scikit-Learn to support data-driven workforce management. The system was developed using Agile Scrum combined with DevOps to enable iterative development and continuous integration. The HRMS consolidates key functions including employee records, payroll management, compensation planning, HMO and benefits administration, attrition risk analysis, and HR analytics dashboards. Machine learning models in Scikit-Learn process employee data to generate predictive insights. The platform is scalable, user-friendly, and responsive to the operational needs of travel and tours organizations. The HRMS generated attrition-risk indicators from attendance, job-performance, and survey data and integrated employee records, payroll, compensation, benefits, and dashboards. An attrition-risk module may assist human-resource planning when predictions are validated and used ethically.

Keywords

human resource management system (hrms), employee attrition, predictive analytics ai, travel and tours