Scribd
Upload
2 views

? Semester 1 – Research, Data Collection, & Model Design

The document outlines a two-semester project focused on optimizing perishable goods distribution through research, data collection, model design, and implementation. Key activities include defining problems, conducting literature reviews, collecting data, designing supply chain networks, applying AI for demand forecasting and route optimization, and evaluating performance metrics. The expected outcomes include optimized transportation routes, reduced logistics costs, improved delivery efficiency, and a prototype supply chain management tool.

Uploaded by

Alex
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
2 views

? Semester 1 – Research, Data Collection, & Model Design

The document outlines a two-semester project focused on optimizing perishable goods distribution through research, data collection, model design, and implementation. Key activities include defining problems, conducting literature reviews, collecting data, designing supply chain networks, applying AI for demand forecasting and route optimization, and evaluating performance metrics. The expected outcomes include optimized transportation routes, reduced logistics costs, improved delivery efficiency, and a prototype supply chain management tool.

Uploaded by

Alex
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

📌 Semester 1 – Research, Data Collection, & Model Design

1. Problem Definition & Objective Setting

○ Understand key challenges in perishable goods distribution (e.g., cold chain


maintenance, short shelf life, dynamic demand).

○ Identify an industry or case study to model (e.g., grocery distribution,


foodservice logistics).

2. Literature Review & Background Research

○ Study existing methods for supply chain network design, logistics


optimization, and AI applications in supply chain.

○ Explore tools and models such as Mixed Integer Linear Programming


(MILP), Genetic Algorithms, Simulations for route and network
optimization.

3. Data Collection

○ Gather data on suppliers, delivery routes, demand patterns, and


transportation costs.

○ Use real-world datasets or simulated data (e.g., open-source supply chain


datasets, Kaggle datasets, or industry reports).

4. Supply Chain Network Design

○ Create a model of the supply chain network, including supplier selection,


warehouses, and distribution points.

○ Design a simulation of the supply chain flow (from suppliers to warehouses


to customers).

5. AI for Demand Forecasting & Inventory Optimization

○ Implement demand forecasting using AI models (ARIMA, Prophet, LSTM,


etc.).

○ Define inventory strategies based on forecasting results (reorder points,


safety stock levels).

6. Simulation Model Design

○ Develop an initial supply chain simulation using tools like AnyLogic, SimPy,
or Arena.

○ Simulate existing supply chain network and identify inefficiencies.

📌 Semester 2 – Model Implementation, Optimization, & Evaluation


7. AI for Route Optimization

○ Apply AI algorithms like Genetic Algorithms, Ant Colony Optimization, or


Dijkstra’s Algorithm to optimize transportation routes.

○ Consider factors like fuel cost, traffic data, delivery time windows, and
capacity constraints.

8. Supply Chain Cost Optimization

○ Develop an optimization model using Linear Programming (LP) or Mixed


Integer Linear Programming (MILP) to minimize costs (transportation,
warehousing, stockouts).

○ Model the impact of different strategies: centralized vs. decentralized


distribution, transportation mode selection, warehouse location.

9. Performance Metrics & Evaluation

○ Evaluate supply chain performance using KPIs like total transportation


cost, on-time delivery rate, service level, inventory turnover, and
environmental impact (CO2 emissions).

10. System Integration and Simulation

○ Integrate demand forecasting with route optimization and inventory


management.

○ Run simulations for different scenarios to test the effectiveness of your


optimization strategies.

11. Dashboard Design & Visualization

○ Build a simple web-based dashboard or visualize results in Power


BI/Tableau to display metrics like supply chain flow, costs, and on-time
deliveries.

○ Present real-time updates on performance during the simulations.

12. Results & Recommendations

○ Analyze results from different models and propose recommendations for


network design, logistics management, and supplier relationships.

○ Compare baseline supply chain strategies with optimized solutions in terms of


cost savings, delivery efficiency, and overall performance.

13. Final Report & Presentation

○ Write a detailed final report covering all aspects of the project: research,
methodology, results, discussions, and future scope.

○ Prepare a presentation for project defense, highlighting key insights and


recommendations.
🧰 Tools You Can Use:
● Programming: Python (Pandas, Scikit-learn, Pyomo, TensorFlow)

● Optimization: Gurobi, CPLEX (for LP/MILP)

● Simulation: AnyLogic, SimPy, Arena, MATLAB

● Visualization: Power BI, Tableau, or custom dashboard (Flask, Streamlit)

● Data Sources: Kaggle, open-source supply chain datasets, industry reports

🎯 Expected Outcomes:
● Optimized transportation routes and supplier selection.

● Reduction in logistics costs and transportation delays.

● Improved on-time deliveries, inventory levels, and service quality.

● Data-driven recommendations for supply chain improvements.

● A prototype supply chain management tool for real-world applications.

Final Thoughts:
This project involves both theoretical and practical work, providing significant insights into
the complexities of perishable goods logistics while integrating AI, optimization
techniques, and simulation models. It’s designed to give you hands-on experience with
real-world supply chain problems while leveraging modern technologies.

You might also like