, my LinkedIn inbox is stuffed with data scientists reaching out.
Same questions. Same concerns. Is supply chain data science the suitable move?
After 10 years in supply chain data science, including five years writing on this blog, I even have developed strong views on this query.
Supply chain is an exceptional playground for data scientists.
Wealthy problems, beautiful mathematics and tangible impacts.
But I’m not here to inform you what’s best on your profession.
In this text, I need to provide an honest view of the opportunities that excite me and the challenges that frustrate me.
More importantly, I’ll show learn how to explore this domain yourself using the tutorials and case studies shared across this blog.
You possibly can then test yourself to see whether supply chain analytics resonates with you.
Why do we want Supply Chain Analytics?
What’s a Supply Chain?
A Supply Chain will likely be defined as several parties exchanging flows of fabric, information or monetary resources with the last word goal of fulfilling a customer request.
Factories, warehouses and planning teams use systems to speak and exchange information.
These systems store a considerable amount of transactional data in databases that reflects the activity of your entire supply chain.
- Warehouse Management Systems (WMS) store all of the inbound and outbound transactions.
- Enterprise Resource Planning (ERP) systems can store all the acquisition orders (to suppliers) and invoices (to customers)
- Transportation Management Systems (TMS) will record all of the shipments leaving the warehouse and notify you once they are delivered.
Because it is unattainable to trace each shipment across the availability chain, these data remain the one technique to monitor your operations.
Due to this fact, Supply Chain Analytics has emerged as a strategy that organisations use to achieve insights from data related to all processes throughout the value chain.
We want to take advantage of this data, but for what?
Descriptive Analytics: Bring Visibility to Operational Teams
At first, corporations need visibility.
In a past experience, I worked with a Logistics Director who couldn’t tell me what number of pallets they’d of their largest distribution centres.
That is where we’re for many corporations in 2026.
I admit, this isn’t as cool as machine learning or advanced optimisation yet.
But it surely’s where most supply chain analytics journeys begin, and where you possibly can deliver immediate value!
I discovered in my first years as a Supply Chain Solution Designer that operational teams were drowning in data but unable to see patterns.
They know something went fallacious, but they’ll’t explain why.
Operations manager: we don’t manage to extend our capability of orders prepared per day and we don’t why!
In a warehouse storing products for a cosmetics retailer, I used to be asked to support the reengineering of operations to extend e-commerce capability.
Around November eleventh, you could have an enormous e-commerce festival in China during which volumes are multiplied by ten.
Operations manager: we recruit more operators however it doesn’t impact the capability.
To seek out the foundation cause, I made a decision to go on-site and observe a shift during peak hours.
And I quickly observed that many operators were packed in some alleys of the warehouse waiting for his or her turn to choose products.
I assumed that was probably the foundation cause, but I needed a technique to prove that and communicate it to the operations manager.
With this heatmap, showing the proportion of orders per storage location, we unlocked the situations by quickly understanding the foundation cause.
They knew that some areas contained high rotation SKUs, but to not this extent.
Operations Manager: we must spread the high rotations across the warehouse to avoid congestion.
This straightforward visualisation, which I learned from EDAs in Kaggle, was the start of a more complex optimisation study that I documented on this series of articles.
Even when this isn’t deep learning or complex optimisation, never underestimate the worth of the correct visualisation solving the suitable operational problem.
The reengineering study that began from this easy visual helped us to renew the contract with this customer and earn several million euros.
What in the event you want more technical challenge?
Diagnostic Analytics: Data supporting Root Cause Evaluation
We will now step up the technical complexity.
Let me introduce a strategy that became my favourite playground for supply chain data science: Lean Six Sigma.
Lean Six Sigma is a step-by-step approach to process improvement that uses statistical tools to validate assumptions.
Why Lean Six Sigma? Since it forces rigour through statistically backed assumptions.
Operations teams make assumptions each day which are most frequently based on their experience, but rarely on data, as they’re too deep within the day-to-day management.
We will support them with statistics using the Lean Six Sigma approach.
I first used this approach for a project supporting the transportation team of a factory in North America.
The Inbound Transportation Manager received products from two different routes.
- Route 1:
- Route 2:
An external service provider allocates the shipment to a pool of drivers (D1, D2, D3).
What’s the issue?
When an order is allocated to the northern regional hub, the lead time for the request to be accepted is 35% higher than on the southern hub.
Transportation Manager: We assume that drivers avoid as much as possible to be allocated to the north route.
Before jumping to conclusions (and starting a conflict with drivers), we decided to analyse the past shipment confirmations.
We used cross-validation and the Chi-Squared test to point out that there isn’t a significant proof that the driving force’s allocation is linked to the Hub.
This helped the team to analyze other potential root causes to unravel the issue.
For more details concerning the approach (and examples with source code), you possibly can have a have a look at these short explainer videos:
With these descriptive and diagnostic tools at hand, you could find the foundation reason behind most operational issues in warehouses, factories, and planning teams.
- Why do we’ve got a drop in productivity with this shift of operators?
- Why are there +20% picking errors on this area?
- Why do we’ve got an extra day of lead time on this specific freight road?
Answering these questions with statistically backed methodologies may help teams implement motion plans.
Can we support these motion plans with data-backed prescriptions?
If we summarise what we’ve seen to this point, in the continual improvement journey, you possibly can
- Help to discover the issue with a fastidiously chosen visualisation
- Communicate the insights to operational teams
- Use statistical methods to search out the foundation cause
It’s time now to offer solution-oriented insights to support operational improvements.
Prescriptive Analytics: Optimisation for Decision Making
The thought here is to unravel an optimisation problem linked to a performance indicator.
It will probably be:
- Team leaders who wish to optimise their hiring of temporary staff
- A planner who expects to extend the trucks’ filling rate
- A warehouse manager who needs to scale back cupboard space
Mainly, we would like to maximise or minimise a particular objective function while respecting particular constraints.
On this blog, you could find dozens of examples using linear and non-linear programming to optimise a particular process.
I’ll use the Supply Chain Network Design problem for example the challenges you might face when conducting this sort of study.
A multinational company with markets and factories in several countries would really like to revamp its supply chain network to scale back costs and environmental footprint.
Their supply chain director expects you to inform them where to open factories to minimise the general production cost.
These are the choice variables in your optimisation model which you could construct using the Python library PuLP.
I faced many issues collecting input data and fixing the target functions.
What are the challenges?
Indeed, more often than not, the issue is rarely stated fully and comprehensively.
As an illustration, in a project for a fashion retailer, it took us weeks to finalise the target function.
Indeed, after presenting the initial results, we noticed that the target of reducing the general production cost (across all countries combined) can affect markets through the Cost of Goods Sold (COGS).
You can’t have scenarios through which it’s costlier to provide in India than within the USA.
That is where I had the chance to support the shopper in adjusting their business and operational assumptions, drawing on my understanding of the model.
These sorts of strategic projects can enable you to shine along with your skills as you directly cope with decision-makers on projects that impact profitability.
Our worth-added here shouldn’t be lines of code, but bridging the gap between business facets and optimisation levers.
For more details, I explain on this video how I exploit AI with an MCP server connected to Claude Desktop to unravel this problem:
And you can too find an entire case study on this Towards Data Science article:
To realize this, you wish a basic understanding of the operations coupled along with your data science skills.
I even have some content for that.
What do you might want to start?
The largest issue I saw when managing analysts and data scientists on analytics projects was their limited understanding of operations.
This creates a trust deficit.
Operational teams might even see data scientists as individuals who’ve never set foot in a warehouse.
You wish operational knowledge to reach supply chain analytics.
To not turn out to be an authority.
But enough understanding to speak effectively, frame problems accurately, and design solutions that truly work in practice.
This implies learning the fundamentals: how warehouses and factories operate, how transportation networks function, how inventory flows through a supply chain.
Here’s where to start out.
Learn Supply Chain Processes with 5-min Explainer Videos.
On this playlist of 40+ short explainer videos, I share a condensed version of my 10 years of experience as an answer design manager and as a logistics performance manager.
It starts with the fundamentals of warehousing and transportation operations.
These videos will give the fundamentals to grasp:
- Warehouse processes: receiving goods (inbound), storage of products (inventory) and shipping of products (outbound)
- Transportation Management: Full Truck Load vs. Less Than a Truck Load, performance indicators and price structures
The main target is operational and financial, as this stays a key concern in logistics operations and is my primary expertise as a Supply Chain Solution Manager.
These videos will provide you with the essential knowledge to grasp many of the logistics-related case studies presented on this blog.
In each of those articles, you could find the answer’s source code linked to a GitHub repository and an explainer video summarising the case study.
What are you able to do with that?
I often advise fiddling with the input data, parameters, and scenarios to adapt the answer to your organization’s problem.
You possibly can be imaginative or ask LLM to generate latest scenarios and mess around with them.
Don’t forget that the target is to develop your technical skills in addition to your operational understanding.
Productise your solutions for higher adoption.
On this blog, we would like to construct solutions that impact operations.
We want to make sure their adoption with a user-friendly deployment.
Due to this fact, I dedicated multiple tutorials and articles to the productisation of algorithms and visualisations.
In my last article, I showed you step-by-step learn how to deploy a listing simulation application using Python’s Streamlit library.
This approach may be used for any of the 50+ analytics solutions shared on this blog.
Do I even have book recommandations?
Yes!
My YouTube Channel is known as Supply Science, a reference to Wallace J. Hopp’s book The Supply Chain Science.
In the event you like mathematics and need to use it to actual operational case studies, this book is for you.
What’s next?!
I hope that you simply at the moment are convinced that you could have every part available to turn out to be a supply chain data scientist whose skills are valued for his or her impact on operations.
As someone who recently began my very own company providing analytics products, I can confirm there may be a necessity for these skills.
And we are able to rejoice working on these sorts of projects!
About Me
Let’s connect on LinkedIn and Twitter. I’m a Supply Chain Engineer who uses data analytics to enhance logistics operations and reduce costs.
For consulting or advice on analytics and sustainable supply chain transformation, be happy to contact me via Logigreen Consulting.
In the event you are occupied with Data Analytics and Supply Chain, have a look at my website.
