This project analyzes global supply chain delivery performance using Python and Power BI. The goal of the analysis is to identify operational risks across regions, shipping modes, and product categories, and to visualize delivery performance through an interactive dashboard.
The project combines data analysis in Python with business intelligence visualization in Power BI to uncover patterns in delivery delays and supply chain inefficiencies.
- Python (Pandas, NumPy, Matplotlib)
- Jupyter Notebook
- Power BI
- CSV Data Processing
The dataset contains detailed information about orders, shipping modes, delivery status, product categories, sales, and shipping times.
Key variables include:
- Order Region
- Shipping Mode
- Delivery Status
- Late Delivery Risk
- Sales
- Product Category
- Shipping Delay
The dataset was loaded and analyzed using Python in Jupyter Notebook.
Main steps included:
- Importing and cleaning the dataset
- Selecting relevant columns
- Calculating shipping delay
- Exploring delivery risk patterns
- Generating exploratory visualizations
Key Python libraries used:
- Pandas
- NumPy
- Matplotlib
Several analyses were performed to understand delivery risk patterns, including:
- Late delivery risk distribution
- Delivery risk by region
- Delivery risk by shipping mode
- Product category risk analysis
- Shipping delay distribution
These analyses helped identify the major operational risk areas in the supply chain.
A multi-page Power BI dashboard was created to visualize the insights.
The dashboard contains three main sections:
This page provides a high-level overview of supply chain performance using key metrics and visualizations.
Key metrics:
- Total Sales
- Total Orders
- Late Delivery Percentage
- Average Shipping Delay
Visualizations include:
- Late Delivery Risk by Region
- Shipping Mode Risk
This page uses a scatter plot to analyze delivery risk across product categories.
The visualization compares:
- Average Shipping Delay
- Late Delivery Risk
- Sales Impact
Each bubble represents a product category.
This page focuses on delivery timing performance.
Visualizations include:
- Shipping Delay Distribution
- Order Distribution by Delivery Status
- Average Shipping Delay by Shipping Mode
These charts help understand how severe delivery delays are and which shipping methods contribute most to delays.
Some of the main findings from the analysis include:
- Over 54% of orders carry a late delivery risk, indicating potential supply chain inefficiencies.
- First Class shipping shows the highest delay risk, suggesting premium shipping options may not always guarantee faster delivery.
- Certain product categories, such as Golf Bags & Carts and Lacrosse equipment, exhibit significantly higher delivery risk.
- Most delivery delays are relatively small, with many shipments arriving within one day of the scheduled delivery time.
This repository contains the following files:
- Supply_Chain_Risk_Analysis.ipynb
- supply_chain_cleaned_data.csv
- dashboard_overview.png
- category_risk_analysis.png
- delivery_performance.png
This project demonstrates how data analytics and business intelligence tools can be used to analyze supply chain performance and identify operational risks.
By combining Python-based data analysis with Power BI dashboards, the project provides a clear view of delivery performance across regions, shipping methods, and product categories.