Developing Automated Workforce Scheduling System Using Machine Learning

Developing Automated Workforce Scheduling System Using Machine Learning

Mridul Singhal1, Priyanshu Sharan2, Joy Sachdeva3, Aniket Meena4, Karan5, Dr. Anurag Gupta6

1Mridul Singhal, Student, Department of Mechanical Engineering, Faculty of Engineering, Dayalbagh Educational Institute (Deemed University), Dayalbagh, Agra-282005, Uttar Pradesh, India

2Priyanshu Sharan, Student, Department of Mechanical Engineering, Faculty of Engineering, Dayalbagh Educational Institute (Deemed University), Dayalbagh, Agra-282005, Uttar Pradesh, India

3Joy Sachdeva, Student, Department of Mechanical Engineering, Faculty of Engineering, Dayalbagh Educational Institute (Deemed University), Dayalbagh, Agra-282005, Uttar Pradesh, India

4Aniket Meena, Student, Department of Mechanical Engineering, Faculty of Engineering, Dayalbagh Educational Institute (Deemed University), Dayalbagh, Agra-282005, Uttar Pradesh, India

5Karan, Student, Department of Mechanical Engineering, Faculty of Engineering, Dayalbagh Educational Institute (Deemed University), Dayalbagh, Agra-282005, Uttar Pradesh, India

6Dr. Anurag Gupta, Assistant Professor, Department of Mechanical Engineering, Faculty of Engineering, Dayalbagh Educational Institute (Deemed University), Dayalbagh, Agra-282005, Uttar Pradesh, India

Abstract - Workforce scheduling in manufacturing environments is a critical factor that directly influences productivity, operational efficiency, and cost management. Traditional scheduling methods, such as manual processes and linear programming, often struggle to meet the needs of dynamic industries where sudden changes in demand and employee availability are common. This paper introduces an Automated Workforce Scheduling System (AWSS) using a Python-based program that employs multivariable regression algorithms to optimize workforce allocation. The AWSS leverages worker data, including skillsets, shift preferences, and operational demands, to generate schedules that meet constraints such as required skill coverage, cost minimization, and real-time adaptability to changes like absenteeism or spikes in workload. The system also provides a flexible solution to address inefficiencies present in traditional scheduling methods.

Keywords- Automated workforce scheduling, multivariable regression, labour optimization, manufacturing, real-time rescheduling, dynamic scheduling, Python, AI-driven workforce management