Supply chain systems manage various phases of delivering products to customers, such as material storage, production, fulfillment, and more. Successfully predicting product back-orders in supply chain systems is crucial, as it helps optimize resource allocation for labor, materials, and machinery, enables expediting orders from alternative suppliers to reduce lead time, fulfills contractual obligations, builds good relationships with suppliers, improves data-driven decision making, manages risks associated with supply chain disruptions such as transportation delays and unexpected demand spikes, minimizes costs caused by rush orders and overtime labor expenses, and increases customer satisfaction with timely product delivery. In this module, we will apply the Hybrid Quantum Random Forest model to identify patterns related to backorders, which minimize delays and increase customer satisfaction rate. The model will be trained using training data to discover patterns and correlations between features and their labels. The trained model makes predictions on the test data, and its accuracy is evaluated by comparing the anticipated labels to the actual labels. To implement the model, we will set essential parameters such as the number of qubits and apply multiple Quantum packages and functions.
Learning objectives: after completing this module, students will be able to
(i) describe the products back-order and its types
(ii) explain the importance of predicting products back-order
(iii) apply the knowledge learned in this module to analyze and predict product back-order using various quantum machine learning models