
A Supply Chain can be defined as several parties exchanging flows of material, information or money resources to fulfil a customer request.

Supply chain Analytics includes methodologies and tools organizations use to get insights from data associated with all processes included in the value chain.
As an analytics expert, how can you leverage data to optimize the supply chain of your organization?
In this article, we will introduce the different types of Supply Chain Analytics with Python and understand their impact on the efficiency of your end-to-end operations.
SUMMARY
I. Supply Chain Analytics for Fashion Retail
1. Supply Chain Network of a Fashion Retailer
Example of a Supply Chain for a Fashion Retailer
2. Flows of information
Extract insights for your systems
II. What are the different types of Supply Chain Analytics?
1. Descriptive analytics
Understand what happened?
2. Diagnostic analytics
Why it happened?
3. Predictive analytics
How it will be in the future?
4. Prescriptive analytics
What can we do to minimize X or maximize Y?
5. Generative AI: GPT x Analytics
III. Why is it so important?
IV. What skills do you need?
Supply Chain Analytics for Fashion Retail
Supply Chain Network of a Fashion Retailer
Let us take the example of an international clothing group that has stores all around the world.
You are a data scientist working for the Supply Chain department.
The company produces **** garments, bags, and accessories in factories in Asia.

Stores are delivered from local warehouses and replenished by factories.

Flow of goods
- Warehouses are replenished with bulk from the factories
- Stores’ orders are picked, packed and shipped from local warehouses
Flows of information
- Sales and merchandising teams collect sales data from the stores
- Planning teams provide demand forecasts and support the production schedule
- Supply planners send orders to the factories using an ERP for warehouse replenishment
- Distribution planners create store replenishment orders to the Warehouse Management System (WMS)
How can we exploit the data generated by these systems?
Let us now explore what tools can be used to optimize the flow of goods using the information available.
What are the Different Types of Supply Chain Analytics?
Supply Chain Analytics can be represented as tools that use information flow to answer questions and support decision-making.

You’ll need specific methodology, mathematical concepts, and analytics tools to answer each type of question.
What happened last week? Let’s check the dashboard.
Descriptive Analytics
A set of tools to provide visibility and a single source of truth across the supply chain to track your shipments, detect incidents and measure the performance of your operations.

The final deliverable is usually a set of dashboards that can be put on the cloud using PowerBI/Tableau, such as a
- Warehouse Workload Report reporting the key indicators to measure a warehouse activity (orders prepared, productivity, logistic ratios)
- Supply Chain Control Tower to track your shipments along your distribution networks
- Transportation Route Analysis to visualize the routing of your past deliveries
👨 💼 POSITIONS INVOLVED
Supply Chain Engineers, Data Analysts, Data Architects, Data Engineers, Product Managers and Business Intelligence Experts
🧰 TOOLS
Cloud computing, Python processing libraries (Pandas, Spark), BI Visualisation tools (Tableau, PowerBI, Google Studio)
Why all the shipments of last week were delivered late?
Diagnostic Analytics
This can be summarized as incident root cause analysis. Let’s take the supply chain control tower as an example.

Thanks to your data architecture, you can track your shipments at each step of the logistic chain.

For instance, the chart above shows that long clearance lead times directly lead to late deliveries.
👨 💼 POSITIONS INVOLVED
Supply Chain Engineers, Data Analysts, Data Engineers, Product Managers
🧰 TOOLS
Cloud computing, Python processing libraries (Pandas, Spark), BI Visualisation tools (Tableau, PowerBI, Google Studio)
If a shipment is delivered late, the root cause analysis consists of checking each time stamp to see where your shipment missed a cut-off time.
The shipment arrived late at the airport. Therefore, it missed the flight!
The analysis process is designed by the operational teams and implemented by data engineers for complete automation.
How many orders are we going to received next week?
Predictive Analytics
Support the operations to understand the most likely outcome or future scenario and its business implications.

For instance, by using predictive analytics, you can estimate the impact of future promotions on store sales volumes to support inventory management.
👨 💼 POSITIONS INVOLVED
Supply Chain Engineers, Data Scientists, Business Experts
🧰 TOOLS
Cloud computing, Python processing libraries (Pandas, Spark), BI
Machine Learning, Statistics
In the example above, data scientists will work with business experts to understand which features can help improve the accuracy of sales forecasts.
What is the optimal route planning to minimize CO2 emissions?
Prescriptive Analytics
Assisted the operations in solving problems and optimizing the resources for efficiency.

Prescriptive analytics are often linked to optimization problems where you must maximize (or minimize) objective functions considering several constraints.
👨 💼 POSITIONS INVOLVED
Supply Chain Engineers, Data Scientists
🧰 TOOLS
Cloud computing, Python processing libraries (Pandas, Spark), BI
Machine Learning, Statistics, Linear Programming, Operations Research tools
Usually, the operational issue is linked to a well-known problem with solutions that can be found in the literature.
For instance, the travelling salesman or the job-shop problems are used in the abovementioned examples.
Have you heard about Generative AI?
Generative AI
With the recent adoption of Generative AI, we can enhance the user experience of any analytics product using large language models.
In another article, I share my explorative journey of LLMs used to boost Supply Chain Analytics.
![Supply Chain Control Tower Agent with LangChain SQL Agent [Article Link] - (Image by Author)](https://towardsdatascience.com/wp-content/uploads/2022/09/0RTow8BDEEH58ehyw.png)
GPTs are a feature introduced recently by OpenAI that allows users to create custom versions of ChatGPT tailored for specific purposes.
What if we replace dashboards with a prompt?
This is an opportunity to create and deploy an agent to automate tasks like Pareto and ABC analyses.

The Supply Chain Analyst" is ** a custom GPT agent designed to automate supply chain analytics tasks and interact with users** using natural language.
This agent can be linked to all the solutions presented in this article to optimize a user experience boosted by LLMs.
Leveraging LLMs with LangChain for Supply Chain Analytics – A Control Tower Powered by GPT
Now that we have a quick overview of the different types of Supply Chain Analytics let’s apply these concepts to solve operational issues.
Why is it important?
The scope of responsibilities of a supply chain manager includes

- Understand and minimize the risks
- Optimize operations to reduce costs
- Provide visibility for resource planning
- Prepare for future scenarios
As data scientist, how can we support them?
We can provide descriptive and diagnostic analytics to understand the current situation.
23% of the orders prepared in warehouse A have been shipped late due to a bottleneck in the packing area.
Predictive analytics will give them visibility into the future, while prescriptive analytics will support your decision-making.
We will have a 30% surge of orders next month in Warehouse B.
You must increase your workforce supply.
Now that we know the impact we could have on the business, what do you need to implement these solutions?
If you prefer watching, have a look at the YouTube tutorial
What skills do you need?
Descriptive Analytics Skills
This will depend on the type of analytics your position is involved in.
You will need basic programming skills to work with unstructured data using Python or VBA.
Data is usually unstructured (in Excel files or PDF reports) or comes from heterogeneous systems.

The first mandatory step is the processing and harmonization of information across these different sources and building descriptive capabilities.
What is the biggest challenge? Data integrity
Even though it is considered the easiest type, descriptive analytics will consume much of your energy (and budget).
What about more advanced types of analytics?
As data scientists, we want to provide value with more advanced solutions like those in my articles.
Learn with Case Studies
After creating a clean source of reliable data, you can build diagnostics, prediction or prescription models.
You can find examples of case studies in the articles listed below
Descriptive AnalyticsQuestion: What happened?
Create interactive visualizations deployed on the cloud for operations and management.
Diagnostic AnalyticsQuestion: What is the root cause of this delay?
Automatically operational questions like
- Why did my shipment arrive late?
- What is the biggest bottleneck in our distribution chain?
Predictive AnalyticsQuestion: How many shipments will we receive next week?
Machine Learning for Retail Sales Forecasting – Features Engineering
Prescriptive AnalyticsQuestion: What is the optimal route to minimize the picking distance?
Optimize Production Planning with Python
Improve Warehouse Productivity using Order Batching with Python
Each case study includes the source code in a GitHub repository with dummy data.
You can get inspiration or build a portfolio to impact the efficiency of supply chains with analytics.
Any question? Feel free to let a comment.
About Me
Let’s connect on Linkedin and Twitter. I am a Supply Chain Engineer who uses 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.
If you are interested in Data Analytics and Supply Chain, look at my website.
💌 New articles straight in your inbox for free: Newsletter 📘 Your complete guide for Supply Chain Analytics: Analytics Cheat Sheet