Offered by the Department of Industrial Engineering and Operations Research

Network design underpins cost-effective, resilient supply chains. This module covers supplier selection methods (WSM, AHP, DEA) and the construction of deterministic and stochastic location-allocation models. You’ll implement mixed-integer programs in Python, evaluate trade-offs between the number of facilities and service levels, and run sensitivity analyses to stress-test your network against disruptions.

Topics Covered:

• Supplier Selection: WSM, AHP, DEA 
• Deterministic Network Design Models 
• Stochastic and Robust Optimisation Approaches 
• Python-Based MILP Formulations 
• Case Exercises: Designing for Cost vs. Resilience

In this module, you’ll master inventory-control frameworks that adapt to real-time data and uncertainty. From dynamic EOQ formulations with time-varying parameters to data-driven Newsvendor models and multi-period stochastic control policies, you’ll build models in Python to compute optimal reorder points and safety stocks. This module will demonstrate how Artificial Neural Networks can learn demand patterns and trigger automated replenishment.

Topics Covered:

• Inventory Performance Metrics
• EOQ with Dynamic Demand and Lead Time
• Newsvendor Models: Feature-Based and ML-Enhanced
• Multi-Period Stochastic Control
• ANN-Driven Inventory Optimisation

This module dives deep into forecasting methods, contrasting classical time-series models (ARIMA, exponential smoothing) with machine learning approaches such as decision trees, SVMs, and neural networks. You’ll learn to measure and minimise forecasting errors, incorporate leading indicators, and even prototype GenAI-driven demand simulators. By the end, you’ll know how to select the right model for a given context and integrate forecasts into planning systems.

Topics Covered:

• Time-Series Forecasting Techniques (ARIMA, ETS)
• Forecast Accuracy and Error Metrics
• Machine Learning Forecasting: Tree-Based, SVM, Neural Networks
• Bass Diffusion and Discrete-Choice Models
• GenAI Applications for Scenario-Based Forecasting

This module will focus on the last mile and beyond as you explore dynamic vehicle-routing problems, multi-modal transportation analytics, and risk-modeling techniques. You’ll learn tobuild learning-based route-planning algorithms, quantify disruption and price volatility risks, and employ GenAI for scenario-based contingency planning.

Topics Covered:

• Dynamic Vehicle-Routing Problem (VRP)
• Transportation Data Analytics and KPI Dashboards
• Disruption Risk Modeling (Natural, Geo-Political)
• Commodity Price and FX Risk Analysis
• GenAI-Assisted Scenario Generation