HOTEL AND RESTAURANT MANAGEMENT SYSTEM: HUMAN RESOURCE 3– TIME AND ATTENDANCE MANAGEMENT, SHIFT SCHEDULING AND ROSTER MANAGEMENT, LEAVE MANAGEMENT WITH PREDICTIVE ANALYTICS USING TENSORFLOW, AND COMPLIANCE AND LABOR LAW ADHERENCE

Abstract

Managing shift work in the hospitality sector is challenging due to variable staff availability, leave requests, and the need to comply with labor laws. Seasonal trends, special events, and economic fluctuations further demand a flexible yet structured HR response—something conventional systems often fail to provide due to limited adaptability and forecasting capabilities. This study proposes the development of an integrated Hotel and Restaurant Management System (HRMS) with core HR modules for Time and Attendance, Shift Scheduling, Leave Management, and Labor Compliance. By incorporating predictive analytics through TensorFlow, the system supports data-driven decision-making to forecast staffing requirements, anticipate absenteeism, and optimize workforce planning. Ultimately, this solution addresses inefficiency, compliance risks, and the lack of workforce insights, equipping HR managers with intelligent tools for proactive, goal-oriented decision-making. This study employs the Agile Scrum methodology to develop a Human Resource Management System (HRMS) for hotels and restaurants. The system includes modules for time tracking, shift scheduling, leave management, and labor law compliance, along with features such as biometric sign-ins and real-time notifications. It also integrates TensorFlow-based predictive analytics to forecast staffing requirements and anticipate absenteeism. Development was guided by daily stand-ups, reviews, and retrospectives to ensure continuous progress. Upon completion, the system was thoroughly tested, documented, and deployed to maximize functionality. The system effectively addressed key HR challenges in hotel and restaurant operations. It automated time tracking, optimized shift scheduling, and streamlined leave management. Compliance features ensured adherence to labor laws through real-time alerts. With TensorFlow integration, the system accurately forecasted staffing requirements and absenteeism, enabling managers to plan proactively. Overall, it improved efficiency, reduced manual workload, and supported smarter, data-driven HR decision-making. This project represents a significant advancement in workforce automation and HR management. By integrating TensorFlow-based predictive analytics with robust biometric authentication, the system streamlines timekeeping, scheduling, and leave management. It provides data-driven insights that enable management to anticipate challenges, optimize staff deployment, ensure compliance, and enhance overall efficiency and operational continuity.