Machine Learning Predictions for Absenteeism in Textile Manufacturing

Abstract

In the contemporary business environment, effective human resource management is critical to organizational success. Absenteeism poses a significant challenge globally, disrupting workflows and reducing productivity. This study investigates the integration of machine learning (ML) techniques to predict and manage absenteeism proactively. Through extensive literature review and analysis of ML algorithms-such as logistic regression, decision trees, random forests, and gradient boosting-we identify optimal approaches for absenteeism prediction. Utilizing a dataset comprising over 8500 instances from a textile factory, we assess algorithm performance and select the most accurate predictor. Our research underscores ML's potential in mitigating absenteeism, emphasizing data-driven decision-making in workforce management. Implementing ML-driven solutions enables organizations to optimize resources, improve operational efficiency, and cultivate a healthier workplace.