Date of Award
Doctor of Philosophy
Agricultural and Biosystems Engineering
Industrial and Agricultural Technology
Steven A. Freeman
Agriculturally related industries are routinely among the most hazardous work environments. Workplace injuries directly impact labor-market outcomes including income reduction, job loss, and health of the injured workers. In addition to medical and indemnity costs, workplace incidents include indirect costs such as equipment damage and repair, incident investigation time, training new personnel for replacement of the injured ones, an increase in insurance premiums for the year following the incidents, a slowdown of production schedules, damage to companies’ reputation, and lowering the workers’ motivation to return to work. The main purpose of incident analysis is the derivation and development of preventative measures from injury data. Applying proper analytical tools aimed at discovering the causes of occupational incidents is essential to gain useful information that contributes in preventing those incidents in future. Insight gained from the analyses of workers’ compensation data can efficiently direct preventative activities at high-risk industries. Since incidents arise from a combination of factors rather than a single cause, research on occupational incidents must go deeper into identifying the underlying causes and their relationship through applying more comprehensive analyses. Therefore, this study aimed at identifying underlying patterns in occupational injury occurrence and costs using data mining and predictive modeling techniques instead of traditional statistical methods. Utilizing a workers’ compensation claims dataset, the objectives of this study were to: investigate the use of predictive modeling techniques in forecasting future claims costs based on historical data; identify distinctive patterns of high-cost occupational injuries; and examine how well machine learning methods work in finding the predictive relationship between factors influencing occupational injuries and workers’ compensation claims occurrence and severity. The results lead to a better understanding of injury patterns, identification of prevalent causes of occupational injuries, and identification of high-risk industries and occupations. Therefore, various stakeholders such as policymakers, insurance companies, safety standard writers, and manufacturers of safety equipment can use the findings of the study to plan for remedial actions and revise safety standards. The implementation of safety measures by agribusiness organizations can prevent occupational injuries, save lives, and reduce the occurrence and cost of such incidents in agricultural work environments.
Fatemeh Davoudi Kakhki
Davoudi Kakhki, Fatemeh, "Predictive analytics in agribusiness industries" (2018). Graduate Theses and Dissertations. 16567.