The Design and Development of a Causal Bayesian Networks Model for the Explanation of Agricultural Supply Chains

Abstract

Agricultural supply chain management depends upon the decision-making to stabilize the market situation. Uncertainties in demand and supply in the market dynamics are the main thread to the management. It then requires product flow and activities to be understood thoroughly and immediately. This task requires comprehensive information, expertise, and processing ability, which are time-consuming and labor-intensive. This research proposes an automatic system framework alongside a Causal Bayesian Networks model for market detection and explanation using streaming data. This research contributes to designing and developing the model by encoding expert knowledge using cause-and-effect assumptions integrating with supply chain ground through. This model can detect the market situation rationally, likewise human logic. The results proved that the proposed model could accurately detect and reasonably explain the event. It illustrates that the model is suitable and ready for application to real-world applications for supporting decision-making in agricultural supply chain management.