Absenteeism at Work
As the economic side of the world continues to grow, so do the demands associated with it. In lieu of these demands, absenteeism at work can lead to interruptions throughout a company or with a company’s workflow. The overarching question is, can these be predicted despite being unintentional or habitual? Excessive absences impact the performance of the company and the individual. One guarantee is these absences can derive from a variety of reasons, whether medical or personal. Another factor in absences require looking into personal lives, work load, distance from work. By using the Absenteeism at Work from UCI Machine Learning Repository, we will attempt to build a machine learning model using Python. From this data set and this research, we demonstrate an ability to predict absentee time based on the reason for the absence, while accounting for the general lifestyle of the employee(s). We intend to evaluate the impacts of the absenteeism on the company and how to bridge the gaps left when a worker is missing. We hypothesize that employees with more severe medical issues will be at the upper range of all absences, and employees with more social occupations are more likely to miss than their less social counterparts. Using R’s modeling capabilities, we present various statistical and graphical observations.