Optimizing Job Rotation through Biorhythm Analysis and Artificial Neural Network (ANN) Methodology

Job rotation is defined as workers rotating between tasks with different exposure levels and occupational demands. Implementing effective job rotation strategies poses challenges, especially in determining the optimal timing and sequencing of rotations to ensure that employees are suitably matched with job roles. Existing studies indicate that many expectations regarding job rotation have not been fully achieved, as the prediction and measurement of its impact on organizational and individual productivity have not been adequately researched. A critical factor influencing individual productivity is the fluctuation in employee performance, driven by the cyclical mental and physical characteristics of employees, known as biorhythms. Current job rotation models do not adequately address biorhythms, which are inherently difficult to predict. No methodologies have been proposed to model, analyze, or predict these fluctuations in the context of job rotation strategies. This research addresses this gap by developing an artificial neural network (ANN) algorithm capable of modeling complex biorhythmic patterns derived from employee performance data. The proposed model refines job rotation strategies by optimizing the alignment between worker capacities and workstation demands. The method is also applied to an industrial case study, demonstrating its applicability and potential to improve overall operational efficiency.