SECURING AGRICULTURAL LABOUR PRODUCTIVITY: AN AI-DRIVEN FRAMEWORK FOR ADDRESSING TRAUMA-INDUCED ABSENTEEISM IN AGRIPRENEUR-LED ENTERPRISES IN SOUTHWEST CAMEROON

Abstract

The main aim of this study was to develop and empirically test an AI-driven framework for identifying, predicting and mitigating trauma-induced absenteeism among agricultural workers in agripreneur-led enterprises in Southwest Cameroon. Data were collected from 288 agricultural workers using structured questionnaires incorporating the PCL-5 and WPAI instruments, semi-structured interviews, and attendance record reviews. Quantitative data were analysed using descriptive statistics and logistic regression, while Random Forest, Support Vector Machine, and Gradient Boosting Machine algorithms were deployed to develop the predictive framework. The findings revealed alarming prevalence of trauma exposure (81.9%), with 68.4% of workers meeting criteria for probable PTSD and 47.9% experiencing trauma-induced absenteeism. Logistic regression confirmed that trauma exposure significantly increased absenteeism likelihood (AOR = 3.82, p < .001), alongside job demands, social support, and access to psychosocial services as significant determinants. The Random Forest model demonstrated excellent predictive accuracy (82.6%, AUC = 0.89), substantially outperforming traditional approaches. The study concludes that AI-driven frameworks can effectively predict trauma-induced absenteeism and enable proactive workforce interventions. Key recommendations include adopting trauma-informed practices, implementing AI-powered predictive tools for early identification of at-risk workers, and integrating psychosocial support into agricultural policies to safeguard productivity in conflict-affected regions.