Create Your Supply Chain Analytics Portfolio to Land Your Dream Job
A guide for students and professionals to build real-world projects and showcase their skills using the Supply Chain Analytics Cheat Sheet. The post Create Your Supply Chain Analytics Portfolio to Land Your Dream Job appeared first on Towards Data Science.
Supply chains are under pressure like never
From climate-driven disruptions to geopolitical shifts, businesses must adapt to rising costs, new trade barriers and growing sustainability demands.
In this new world where supply chains face uncertainty, Supply Chain Analytics is essential to keep resilient operations.
Samir, can you advise me on how to build a supply chain analytics portfolio with actual projects?
Since publishing my first post on Towards Data Science on August 5th, 2020, I’ve frequently received this question from readers on LinkedIn or YouTube.
In this article, I’ll share my perspective—after nine years in the industry—on how I would use my Supply Chain Analytics Cheat Sheet to build a portfolio if I were starting out as a junior data scientist.
The Supply Chain Analytics Cheat Sheet
What is Supply Chain Analytics?
Let’s start by defining the terms we use.
Supply Chain Analytics refers to a set of tools and methodologies used to extract insights from data across all processes in the value chain.
For instance, a retail company may use:
- An ERP to manage procurement, finance and sales
- A Warehouse Management System to manage its distribution centres
- A Transport Management System to manage inbound and outbound freight
As a Supply Chain Solution Manager and Data Scientist in the logistics industry, I have used analytics in international projects to design and optimize supply chain solutions.
I’ve shared many of these methodologies and tools in over 75 articles published on Towards Data Science.
I’ve compiled them into this concise and comprehensive Supply Chain Analytics Cheat Sheet.
What’s Inside the Supply Chain Analytics Cheat Sheet?
Whether you want to reduce distribution costs, minimize your company’s environmental impact, or maximize profitability, you’ll find the answers to your questions here.
How Can Analytics Help Improve Profitability?
Data Analytics to Boost Business Profitability
The first section of the cheat sheet is about data analytics for Business Strategy.
It includes practical case studies on how to use data to support business executives in their strategic decision-making.
For instance, the series of articles, “Business Planning with Python”, is based on a real example of a business managed by my friend.
“We have to refuse orders as we don’t have enough cash to pay suppliers for stock replenishment.”
I built a simulation model based on this insight to help him understand weaknesses in his value chain and uncover growth opportunities.
They illustrate how you can add value to small, medium, and large business owners.
What About Optimizing Supply Chain Operations?
Supply Chain Analytics for Logistics Operations
Having spent years designing, monitoring, and optimizing supply chain solutions, I’ve compiled many case studies focused on warehousing and transportation operations.
In this section, most case studies are based on an actual reengineering project I have conducted in Asia or Europe.
Country Manager: “Samir, we need to reduce warehousing costs by 15% if we want to renew the contract with the retail company XXX.”
They focus on optimizing a specific process in a warehouse (order preparation, value-added services) or transportation operations (routing, scheduling).
Go to the nearest warehouse and ask: ‘What are your problems?’ You can be sure they will find some for you.
Here’s how to get started:
- Review the case studies to understand the problem statement and the solution.
- Pull the source code from my GitHub repository.
- Search for a similar problem in your company
- Adapt the code to build a solution to your specific problem
The code is usually a simple Python script or a jupyter notebook that can be easily adapted.
What if you want to have a greater impact? Focus on a flow optimization.
Data Analytics for Supply Chain Optimization
The main driver of the reengineering projects I have conducted was cost.
Usually, customers tracked logistics costs, i.e. the percentage of turnover spent on logistic operations.
Therefore, we needed to find solutions (as a third-party logistic service provider) to reduce this percentage without impacting our profitability.
What if we delivered to the U.S. East Coast from a warehouse in Charlotte?
The solutions presented in the previous section are too localized. We need to take a step back and consider flow optimization.
These case studies focus on the optimization of goods flow using
- Replenishment rules and forecasting algorithms to optimize inventory
- Linear/Non-Linear programming to match the supply with demand at the lowest cost
- Statistical tools for diagnostic and improvement of specific processes
For some case studies, I have deployed the models in a web application developed for my startup, LogiGreen.
The demo version is publicly available for you to test the models; more information here.
What about sustainability?
If you want to support the green transformation of your company, I have some examples for you.
Supply Chain Analytics for Sustainability
Since my first project focused on sustainability, I was convinced that green transformation was similar to supply chain optimization.
Therefore, you can find 17 examples of optimization solutions using this approach to minimize CO2 emissions or resource usage.
I also decided to cover the reporting side of sustainability with analytics for Life Cycle Assessment, CO2 emissions calculations or ESG reporting.
If you need support getting started with sustainability projects, you’re covered.
Now It’s Your Turn to Build!
If you need a more detailed presentation of the cheat sheet, check out this short YouTube tutorial.
In the next section, I’ll share how I would approach building a portfolio if I were a junior engineer—or someone transitioning into analytics—looking to land a job or freelance project.
Starting your Analytics Portfolio
Let’s assume I’m a junior data scientist aiming to join a major retailer’s Supply Chain Analytics team.
I want to start a project to showcase how I can use my skills to help retailers improve their service and reduce costs.
Advice 1: Start with a Simple Project
For most companies, data maturity in supply chain departments is very low.
That means the implementation of advanced (and complex) algorithms can be very challenging.
Therefore, I would focus on:
- Delivering business value (visibility, insights, diagnostics)
- Smooth user experience of your product or analysis
Therefore, I would pick the topic of ABC Analysis and Product Segmentation.
This article provides multiple examples of analysis to segment products based on their demand variability and contribution to the turnover.
The article includes a link to a GitHub repository with a Jupyter Notebook containing all the necessary code.
Advice 2: Add Business Value
My articles always use generic dummy data to feed the algorithms and visuals generated.
You can enrich this data by adapting it to the industry you’re targeting.
- Fashion retailers usually have seasonality and complex master data
- Cosmetics product categories are an essential demand driver that can affect the results of your forecast engine
Before jumping into the code, show that you can take ownership of the case study and adapt it to your vision of the problem to solve.
Advice 3: Code Refactoring and Packaging
My GitHub code is mostly in the form of Jupyter Notebook or standalone Python scripts.
This is a great opportunity for our junior data scientist to show that he can package the code into an API or even build a web application around it.
Indeed, currently data scientists are expected to ship their models in a form ready for productization.
Consider learning about script packaging, Docker containerization, and API development.
Advice 4: Improve the UI and add insights
Remember, your skills will be judged by the impact of the analytics products you design and deploy.
Therefore, do not hesitate to improve the outputs and insights of the models shared in my cheat sheet.
It is an excellent opportunity to ask your colleagues in supply chain operations how these tools can support them.
- What KPIs are they tracking?
- What kind of insights do they lack to pilot their operations?
From here, this case study is yours to make your own.
If you follow these steps, your portfolio will not be a copy of my GitHub repository but a reflection of your skills and how you can impact businesses.
This is precisely what I did when I built the demo version of the LogiGreen Apps.
The demo version is publicly available for you to test the models and get inspiration: more information here.
I’m looking forward to seeing your version of it!
Conclusion
I hope this brief introduction to the cheat sheet has helped clarify how you can start building your analytics portfolio.
Do not hesitate to bookmark this cheat sheet as I will update it each time a new content is published.
I want to use this article and the YouTube video as a forum to collect your feedback or questions.
Do not hesitate to use the video’s comment section to ask questions!
If you have used any case studies for some of your projects, I would be happy to learn more about the results.
About Me
Let’s connect on Linkedin and Twitter; I am a Supply Chain Engineer using data analytics to improve Logistics operations and reduce costs.
For consulting or advice on analytics and sustainable Supply Chain transformation, feel free to contact me via Logigreen Consulting.
The post Create Your Supply Chain Analytics Portfolio to Land Your Dream Job appeared first on Towards Data Science.
