As a Data Scientist, if you want to use Data to impact your organization, contribute to large-scale operations, and see your models used to implement concrete solutions, Supply Chain is the best candidate to start your Data Science Journey.
I have been working in Supply Chain for more than 8 years with a great focus on Warehousing and Transportation Operations.
As a Supply Chain Solution Designer, my job was to
- Translate our customer's requirements into actual operational solutions (Retail, E-Commerce, Luxury, FMCG, Automotive)
- Conduct re-engineering studies to improve warehouse operations and optimize transportation networks.
The common point of all these projects was the leverage I got by using data science tools to simulate thousands of scenarios and the ability to build predictive and prescriptive analytics models for Supply Chain operations.
In this article, you can find 22 major Supply Chain case studies (edit: I have added additional examples) that can be applied to your operations by following detailed tutorials.
For each example, I share the source code with dummy data so you can adapt the model for your projects.
Tips for Students
You can use any of these examples as a basis to build your portfolio.
💌 New articles straight in your inbox for free: Newsletter
📘 Your complete guide for Supply Chain Analytics: Analytics Cheat Sheet
I. How do you automate supply chain analytics with GPTs?
OpenAI introduced a new feature allowing users to create custom versions of ChatGPT tailored for specific purposes.
This is an opportunity for me to easily create and deploy an agent to automate Pareto and ABC analyses.
Objective: Introducing “The Supply Chain Analyst”, a custom GPT agent designed to automate supply chain analytics tasks and interact with users using natural language.
II. What is Supply Chain Analytics?
Objective: Use data analytics with Python to improve operational efficiency by enabling data-driven diagnostics and decisions at strategic and operational levels.
A Supply Chain can be defined as several parties exchanging flows of material, information or money resources to fulfil a customer request.
As information plays an important role, Supply chain Analytics has emerged as the methodologies and tools organizations use to get insights from data associated with all processes included in the value chain.
In this video, you will discover the different types of Supply Chain Analytics with Python and understand their impact on the efficiency of your end-to-end operations so you can start your project.
III. How to Leverage Data Analytics for Sustainability?
Sustainability has become a critical aspect of business operations as companies face mounting pressure to address environmental and social issues for their ESG reporting.
Experts exposed the barriers that companies face in their pursuit of sustainability, focusing on four “hidden enemies”:
- Structure and Governance: Siloed sustainability limits influence.
- Processes and Metrics: Unsustainable metrics hinder progress.
- Culture and Leadership: Old mindsets challenge transformation.
- Methods and Skills: Traditional tools obstruct change.
Problem Statement: As a data scientist, analyst, or continuous improvement engineer, how can your company boost its green business transformation?
Objective:
Explore how data analytics can help to overcome these challenges by focusing on the four “hidden enemies” of your Supply Chain green transformation.
💡 Follow me on Medium for more articles related to 🏭 Supply Chain Analytics, 🌳 Sustainability and 🕜 Productivity.
IV. How Sustainable is Your Circular Economy?
Scope: Supply Chain Sustainability
Key Skills: Inventory Management, Life Cycle Analysis, CO2 Emissions Calculation, Supply Chain Descriptive Analytics (Data Processing, Visualization and KPI creation)
Problem Statement:
A circular economy is an economic model that aims to minimize waste and maximize resource efficiency.
It involves designing products and processes focusing on longevity, reuse, and recycling.
Some companies have implemented a subscription model where customers pay a regular fee to access a product or service for a specific period.
Objective: Use data analytics to simulate the impacts of several scenarios of circular subscription models on emissions reductions and water usage of a Fast Fashion Retailer.
V. What is Green Inventory Management?
Scope: Supply Chain Sustainability
Key Skills: Inventory Management, CO2 Emissions Calculation, Supply Chain Descriptive Analytics (Data Processing, Visualization and KPI creation)
Problem Statement:
Green inventory management can be defined as managing inventory in an environmentally sustainable way.
A distribution network can involve processes and rules to reduce the environmental impact of order transmission, preparation and delivery.
What would be the impact on CO2e emissions if we reduce the frequency of store replenishments?
Objective: Use data analytics to simulate the variation of store replenishment frequency and measure the impact on the overall environmental impact.
VI. How to Optimize Production Planning with Python?
Scope: Manufacturing
Problem Statement: The master production schedule is the main communication tool between the commercial team and production.
Your customers send purchase orders with specific quantities to be delivered at a certain time.
Production planning is used to minimize the total cost of production by finding a balance between minimizing inventory and maximizing the quantity produced per setup.
Objective: In this article, we will implement optimal production planning using the Wagner-Whitin method with Python.
VII. How to Automate Supply Chain Sustainability Reporting with Python?
Scope: Sustainability
Problem Statement: The demand for transparency in sustainable development from investors and customers has grown.
Investors have increasingly emphasised the business's sustainability when assessing an organisation's value and resiliency.
Therefore, more and more organizations invest resources to build capabilities for sustainability reporting and determine the best strategies for a sustainable supply chain.
Objective: In this article, we will introduce a simple methodology to report the CO2 emissions of your Distribution Network using Python and PowerBI.
VIII. What is Supply Chain Network Optimization?
Scope: Supply Chain Optimization
Problem Statement: Supply chain optimization uses data analytics to find an optimal combination of factories and distribution centres to meet your customers' demands.
The core structure of many software and solutions in the market is a Linear Programming Model.
Some of these models find the right allocation of factories to meet the demand and minimize the costs, assuming a constant demand.
What happens if the demand is fluctuating?
Your network may lose robustness, especially if you have a very high seasonality of your demand (e-commerce, cosmetics, fast fashion).
Objective: In this article, we will build a simple methodology to design a Robust Supply Chain Network using Monte Carlo simulation with Python.
IX. Implement Machine Learning for Retail Sales Forecasting with Python
Scope: Demand Forecasting
Problem Statement: Based on the feedback of the last Makridakis Forecasting Competitions, machine learning models can reduce forecasting errors by 20% to 60% compared to benchmark statistical models. (M5 Competition)
Their major advantage is the capacity to include external features that heavily impact the variability of your sales.
For example, e-commerce cosmetics sales are driven by special events (promotions) and how you advertise a reference on the website (first page, second page, …).
Feature engineering is based on analytical concepts and business insights to understand what could drive your sales.
Objective: In this article, we will try to understand the impact of several features on the accuracy of a model using the M5 Forecasting competition dataset.
X. How to Improve Warehouse Picking Productivity with Python?
Scope: Warehouse Operations
Problem Statement: In a Distribution Center (DC), walking time from one location to another during the picking route can account for 60% to 70% of the operator’s working time.
Objective: How can you use Data Science to increase Warehouse Operators’ productivity by reducing walking distance?
I have written several articles explaining how to use Order Batching, Spatial Clustering and Pathfinding Algorithms to improve picking productivity.
Concept & Libraries Used:
- Create Orders Batch using Python’s Pandas, Numpy
- Spatial Clustering of Picking Location using Python’s Scipy
- Pathfinding for Picking Route design using Google OR
Results: An increase in your operators’ picking productivity will lead to cost reductions
Link to the Articles
XI. How to Automate Ressources Planning and Scheduling with Python?
Scope: Warehouse Operations
Problem Statement: What is the minimum number of temporary workers you need to hire to absorb your weekly workload while ensuring employee retention?
Objective: Following the productivity targets fixed by your manager, you must minimize the number of workers hired to handle the workload.
I have written a medium article on using Linear Programming to find the right number of workers to hire.
Concept & Libraries Used:
- Linear Programming with Python’s PuLP
Results: Calculate the minimal number of workers that respects all the constraints.
XII. Transportation Route Optimization with Python
Scope: Transportation Operations
Problem Statement: How do you organize the delivery routes and truck loading to reduce your costs?
Objective: Visualisation and Costing of your Transportation Plan to optimize the loading rate and reduce the costs per ton of your Transportation.
I have written a medium article on processing data and preparing visualization to impact the average cost per ton of your deliveries.
Concept & Libraries Used:
- Data Processing with Numpy, Pandas and visualization with Matplotlib (Link)
Results: An Optimized transport plan using larger trucks with a higher loading rate.
💡 Follow me on Medium for more articles related to 🏭 Supply Chain Analytics, 🌳 Sustainability and 🕜 Productivity.
XIII. How do you implement Lean Six Sigma with Python using the Kruskal Wallis Test?
Scope: Warehouse Operations
Lean Six Sigma (LSS) is based on a stepwise approach to process improvements following 5 steps (Define, Measure, Analyze, Improve and Control).
As a continuous improvement Manager of a Distribution Center (DC) for an iconic Luxury Maison, you want to use this approach to improve the productivity of a specific process.
Question
Does the training have a positive impact on the productivity of operators?
Hypothesis
The training has a positive impact on the productivity of VAS operators.
Experiment
Randomly select operators and measure the time per batch (Time to finish a batch of 30 labels in seconds) to build a sample of 56 records.
Objective: In this article, we will explore how Python can replace Minitab in the Analysis step to test hypotheses and understand what could improve the performance metrics of a specific process.
XIV. Deploy Interactive Dashboard using Python Flask and javascript D3.js
A simple and fancy visualization can impact more than a very complex model, especially for a non-technical audience.
Therefore, building your visualization skills is important to your Supply Chain Data Scientist job.
Scope: Visualization & Reporting
I have written a medium article on designing fancy visualization using D3.js without prior knowledge of JavaScript (or very light).
Concept & Libraries Used:
- Data Processing with Numpy, Pandas, Flask and D3.js (Link)
Results: A dynamic dashboard that can interact with users to show business insights.
XV. How do you Optimize Inventory Management for Retail with Python for a Stochastic Demand?
Scope: Inventory Management
Problem Statement: For most retailers, inventory management systems take a fixed, rule-based approach to forecast and replenishment order management.
Considering the demand distribution, the objective is to build a replenishment policy to minimize your ordering, holding and shortage costs.
In a previous article (Link), we built a simulation model assuming a deterministic constant demand (Units/Day).
Objective: In this article, we will introduce a simple methodology using a discrete simulation model built with Python to test several inventory management rules assuming a normal distribution of customer demand.
XVI. Transportation Network Analysis with Python using Graph Theory
Scope: Road Transportation
Objective: Build Visuals to support FTL routing optimization
Problem Statement: For a retailer, road transportation to deliver stores represents a major part of the logistics costs.
Companies often conduct route planning optimization studies to reduce these costs and improve the efficiency of their network.
It requires collaboration between continuous improvement engineers and the transportation teams managing daily operations.
Objective: In this article, we will use Graph Theory to design visual representations of a transportation network to support this collaboration and facilitate solution design.
XVII. Sustainable Supply Chain Optimization Application
Scope: Sustainability
Objective: Help your organization combine sustainable sourcing and supply chain optimization to curb costs and environmental impacts.
I developed an application using the VIKTOR platform to facilitate data-driven decision-making for optimizing supply chain network sustainability.
Access it here,
XVIII. How to Automate ESG Reporting with Python?
Scope: Sustainability
Objective: Comprehensive and effective environmental, social and governance reporting of a company
Environmental, Social and Governance (ESG) reporting is a method companies use to disclose their governance structures, societal impacts and environmental footprint.
As stakeholders increasingly demand corporate social responsibility (CSR), ESG reporting has become critical to companies’ long-term strategies.
XIX. How to fight Greenwashing with Python?
Scope: Sustainability
Objective: delve into the world of greenwashing to explain its manifestations and how to use data analytics to detect and prevent these unethical practices.
Greenwashing is the practice of making misleading claims about the environmental benefits of a product or a service to communicate a false image of sustainability.
XX. Leveraging LLMs with LangChain for Supply Chain Analytics
Scope: Generative AI
Objective: Master Langchain with OpenAI’s GPT models and build the ultimate Supply Chain Control Tower.
Create a LangChain agent connected to a local database to answer operational questions using data.
Conclusion
These examples can be directly applied to your operations using your data sets to provide insights that will impact your organization quickly.
Feel free to leave questions in the comment section.
You can follow me on Medium for more articles related to Data Science for Supply Chain Optimization.
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.
If you are interested in Data Analytics and Supply Chain, look at my website.
References
[0] Samir Saci, My GitHub Portfolio, Link
