Supply Chain Analytics (BIT472MS)

Data analytics and machine learning applied to supply chain management — data preparation in Python, Seaborn visualization, customer RFM segmentation, supplier risk, and demand forecasting.

1. Unit 1: Introduction to Supply Chain Analytics4 hrs

   • Definition of Supply Chain and need for supply chain management
   • Structure of supply chains, processes, flows, and strategic decision making
   • Supply chain analytics definitions, value proposition, and role of AI
   • Defining SMART goals and KPIs for supply chain optimization

2. Unit 2: Data-Driven Supply Chains with Python5 hrs

   • Data-driven decision making in supply chain environments
   • Setting up the Python analytics runtime environment (Jupyter, NumPy, Pandas)
   • Structure of tabular data, variables, and series data types
   • Data cleaning, outlier treatment, and missing value imputation in supply datasets

3. Unit 3: Data Manipulation & Indexing in Python5 hrs

   • Pandas data manipulation: indexing, slicing, filtering, and grouping
   • Data aggregation, pivoting, and merging disparate logistical datasets
   • Feature engineering for delivery performance and transit time calculations

4. Unit 4: Data Visualization & Geospatial Analysis5 hrs

   • Exploratory data visualization using Seaborn and Matplotlib
   • Distribution plots, correlation heatmaps, and trend analysis
   • Geospatial visualization of supplier locations, transport corridors, and delivery zones

5. Unit 5: Customer Management & RFM Segmentation6 hrs

   • Customer relationship analytics in supply chain operations
   • Customer cohort analysis and churn prediction
   • Recency, Frequency, Monetary (RFM) customer segmentation
   • k-means clustering for behavioral customer categorization

6. Unit 6: Supply Management & Supplier Risk Analysis5 hrs

   • Procurement analytics and supplier performance scorecarding
   • Assessing supplier delivery risk using multiple linear regression and logistic regression
   • Lead time variability analysis and supplier reliability benchmarking

7. Unit 7: Warehouse and Inventory Optimization5 hrs

   • Inventory management metrics: Economic Order Quantity (EOQ), Reorder Point (ROP), Safety Stock
   • ABC and XYZ inventory classifications
   • Warehouse slotting optimization and picking path efficiency

8. Unit 8: Demand Forecasting5 hrs

   • Importance of demand forecasting in mitigating the Bullwhip Effect
   • Quantitative time series methods: Moving Averages, Exponential Smoothing (Holt-Winters)
   • Evaluating forecast accuracy: MAD, MSE, RMSE, and MAPE metrics

9. Unit 9: Logistics Management & Route Optimization5 hrs

   • Transportation modes, freight logistics, and carrier selection
   • Logistics network design and facility location decisions
   • Route optimization fundamentals and Vehicle Routing Problem (VRP) solving with Python