# Supply Chain Analytics in Python

Leverage the power of Python and PuLP to optimize supply chains.

4 Hours16 Videos48 Exercises

or

## Course Description

Supply Chain Analytics transforms supply chain activities from guessing, to ones that makes decision using data. An essential tool in Supply Chain Analytics is using optimization analysis to assist in decision making. According to Deloitte, 79% of organizations with high performing supply chains achieve revenue growth that is significantly above average. This course will introduce you to PuLP, a Linear Program optimization modeler written in Python. Using PuLP, the course will show you how to formulate and answer Supply Chain optimization questions such as where a production facility should be located, how to allocate production demand across different facilities, and more. We will explore the results of the models and their implications through sensitivity and simulation testing. This course will help you position yourself to improve the decision making of a supply chain by leveraging the power of Python and PuLP.
1. 1

### Basics of supply chain optimization and PuLP

Free

Linear Programming (LP) is a key technique for Supply Chain Optimization. The PuLP framework is an easy to use tool for working with LP problems and allows the programmer to focus on modeling. In this chapter we learn the basics of LP problems and start to learn how to use the PuLP framework to solve them.

Play Chapter Now
Basics of optimization
50 xp
To LP, or to not IP?
50 xp
Choosing exercise routine
50 xp
Basics of PuLP modeling
50 xp
Getting started with LpProblem()
50 xp
Simple resource scheduling exercise
100 xp
Using lpSum
50 xp
Trying out lpSum
100 xp
Logistics planning problem
100 xp
2. 2

### Modeling in PuLP

In this chapter we continue to learn how to model LP and IP problems in PuLP. We touch on how to use PuLP for large scale problems. Additionally, we begin our case study example on how to solve the Capacitated Plant location model.

3. 3

### Solve and evaluate model

This chapter reviews some common mistakes made when creating constraints, and step through the process of solving the model. Once we have a solution to our LP model, how do we know if it is correct? In this chapter we also review a process for reasonableness checking or sanity checking the results. Furthermore, we continue working through our case study example on the Capacitated Plant location model by completing all the needed constraints.

4. 4

### Sensitivity and simulation testing of model

In our final chapter we review sensitivity analysis of constraints through shadow prices and slack. Additionally, we look at simulation testing our LP models. These different techniques allow us to answer different business-related questions about our models, such as available capacity and incremental costs. Finally, we complete our case study exercise and focus on using sensitivity analysis and simulation testing to answer questions about our model.

Collaborators

Prerequisites

Data Manipulation with pandas
Aaren Stubberfield

Senior Data Scientist @ Microsoft

I am a Senior Data Scientist with expertise in Machine Learning, AI, and data governance. Currently, I work for Microsoft's Digital Advertising, which has revenues of more than \$10 billion in the fiscal year 2023. However, my experience is not limited to just the advertising industry. I have worked in the Supply Chain and Data Governance industries. With my vast experience, I have led numerous teams of data scientists and have been instrumental in the successful completion of many projects. My technical skills include the use of AI, like LLMs, Python, and other various tools necessary for the execution of data science projects. My passion lies in using data to gain insights and making data-driven decisions. I constantly strive to improve my skills and knowledge and am always open to learning new techniques and tools.
See More