Predictive machine learning for supply chain data analytics is reported as a significant area of investigation due to the rising popularity of the AI paradigm in the industry. We can explore how machine learning can be used in predicting first tier supply chain disruptions using historical performance data. The methodology involves three steps:
Current results indicate that adding engineered features in the data, namely agility outperforms other experiments leading to the final algorithm that can predict late orders with 80% accuracy, which could be added by FedEx to boost this development and reduce the impact of any upcoming global supply chain disruptions.
An exploratory phase is conducted to select and engineer potential features that can act as useful predictors of disruptions.
Developing performance metrics in alignment with the specific goals of the case study to rate successful methods.