Coupling simulation and machine learning for predictive analytics in supply chain management
针对传统预测方法在供应链中难以应对不确定性和复杂性的问题，提出将仿真与机器学习耦合的集成预测分析方法，并在人道主义供应链中应用，以有限历史数据开发预测模型，支持危机前绩效评估和及时决策。
Predictive analytics is the approach to business analytics that answers the question of what might happen in the future. Although predictive information is critical for making forward-looking decisions, traditional approaches struggle to cope with the increasing uncertainty and complexity that characterise modern supply chains. Simulation is limited by insufficient timeliness, while machine learning is constrained by poor interpretability and data scarcity. Inspired by the complementary nature of simulation and machine learning, an integrated predictive analytics approach is proposed and applied to a humanitarian supply chain. By coupling simulation and machine learning, predictive models can be developed with limited historical data, and pre-crisis performance assessment can be performed to facilitate timely and informed decisions. The proposed approach enables managers to gain valuable insights into the complex evolution of the uncertain future, which also opens up the possibility of further integration with optimisation and digital twins.