Abstract
For many businesses, preventing food waste along the whole supply chain has become a big issue. Customers' interest in learning more about the source and origin of the food they consume develops along with their understanding of environmental challenges. This work identified a research gap in the field-specific literature and posed the research question of whether the generally beneficial effects of smart farming, in particular, food tracing technologies, will be aberrative when examined in the context of individual situations. K-means clustering and principal component analysis (PCA) were employed to analyze the logistics system of a chosen dairy product company. This study provides a foundation for further investigation into the system's potential and to uncover new ways of streamlining digital logistics. It was demonstrated that the chosen food logistic system is highly influenced by the three parameters of "temperature for products transportation", "season of time", and "marketing". Utilizing AI to incorporate these factors in the conservative food tracing system resulted in an increase in supply chain management accuracy by 95.6% and 97.7%, respectively. The findings of the research can be applied to other fields of agricultural logistics that have particular transportation requirements. Keywords: food tracing, smart farming, artificial intelligence, dairy company