Abstract: Successful supply chain optimization must mitigate imbalances between supply and demand over time. To successfully perform supply planning for optimal and viable execution, the predictability for both demand and supply is essential. However, in complex supply chain networks with numerous nodes and edges, accurate supply predictions are challenging due to dynamic node interactions, cascading supply delays, resource availability, production, and logistic capabilities. Consequently, supply executions often deviate from their initial plans. A Graph-based Supply Prediction (GSP) probabilistic model is presented. The attention-based graph neural network (GNN) model predicts supplies, inventory, and imbalances using graph-structured historical data, demand forecasting, and original supply plan inputs.

Abstract: A universal deep probabilistic decision-making framework for dynamic process modeling and control, referred to as Deep Probabilistic Decision Machines (DPDM), is presented. A predictive model enables the generative simulations of likely future observation sequences for future or counterfactual conditions and action sequences given the process state. Then, the action policy controller, also referred to as decision-making controller, is optimized based on predictive simulations. The optimal action policy controller is designed to maximize the relevant key performance indicators (KPIs) relying on the predicted experiences of sensor and target observations for different actions over the near future.

Abstract: A universal deep probabilistic decision-making framework for dynamic process modeling and control, referred to as Deep Probabilistic Decision Machines (DPDM), is presented. A predictive model enables the generative simulations of likely future observation sequences for future or counterfactual conditions and action sequences given the process state. Then, the action policy controller, also referred to as decision-making controller, is optimized based on predictive simulations. The optimal action policy controller is designed to maximize the relevant key performance indicators (KPIs) relying on the predicted experiences of sensor and target observations for different actions over the near future.