An AI-enabled Approach to Predict Critical Components and Enhance Supply Chain Management

Ensuring a consistent supply of components is critical in complex manufacturing sectors like automotive production, where component shortages can lead to production stoppages and additional costs. Leveraging cutting-edge technologies offers a promising solution to optimize supply chain operations and proactively address potential obstacles. This research addresses these challenges and proposes an Artificial Intelligence approach to enhance component supply management. We utilized various machine learning algorithms, and the best model was developed using gradient-boosting machines (GBM). This model has demonstrated exceptional performance, achieving an accuracy of $\mathbf{9 6. 6 \%}$, precision of $\mathbf{8 2. 1 \%}$, recall of $\mathbf{9 5. 4 \%}$, and F 1 -score of $\mathbf{8 8. 3 \%}$. These results signify a substantial advancement over conventional methods, manifesting an improvement of over $\mathbf{1 7. 2 9 \%}$ in precision, along with a 10.51% improvement in F1-score. Furthermore, the model’s results were translated into understandable charts and tables in a business intelligence system, ensuring practical usability for non-technical end-users. Finally, the model provides immediate warnings for critical component supply through SMS alerts, empowering supply managers to make timely decisions.