PREDICTIVE AI MARKETING ANALYTICS AND AGRIBUSINESS PROJECT SCALING: AN EMPIRICAL ASSESSMENT OF SEASONAL WORKFORCE STABILITY IN THE NORTHWEST REGION OF CAMEROON

Abstract

This study examined the relationship between predictive AI marketing analytics adoption and seasonal workforce stability, and assessed the influence of workforce stability on agribusiness project scaling in the Northwest Region of Cameroon. A cross-sectional survey of 201 agribusiness enterprises was conducted using structured questionnaires. Regarding sample selection, the study population comprised 320 registered agribusiness enterprises. Cochran's (1977) finite population formula yielded a target of 175 firms, inflated by 15% to 201 to mitigate non-response bias. Stratified random sampling was applied using enterprise operational scale as the stratifying criterion, with simple random sampling via computer-generated numbers within each stratum. Data were collected through structured, closed-ended electronic questionnaires designed on a 5-point Likert scale (1 = Strongly Disagree to 5 = Strongly Agree). Data collected were analyzed using Ordinary Least Squares regression, supported by post-estimation diagnostics. The findings establish that predictive AI analytics significantly relates to workforce stability (R² = 0.262, p < 0.001), with data integration capabilities (β = 0.312, p < 0.01) and forecasting accuracy (β = 0.261, p < 0.01) as key predictors. Workforce stability significantly influences project scaling (R² = 0.237, p < 0.001), with seasonal supply consistency (β = 0.307, p < 0.01) and workforce retention (β = 0.276, p < 0.01) as primary contributors. The study recommends that agribusiness enterprises invest in data integration and forecasting systems, while development agencies implement interventions to enhance workforce retention and seasonal labour supply consistency.