This project presents an in-depth analysis of an e-commerce dataset from Google BigQuery's public dataset, The Look E-commerce Dataset. The analysis aims to uncover insights into sales performance, customer behavior, geographic distribution, and traffic source effectiveness.
- Dataset: The Look E-commerce Dataset
- Location: Available publicly on Google BigQuery
- Link: The Look E-commerce Dataset on BigQuery
- Data Import: The dataset was accessed through BigQuery and imported into Power BI for analysis.
- Data Cleaning:
- Handled missing values and ensured data consistency across all tables.
- Standardized data types, particularly for date fields and numerical values, to enable accurate calculations and comparisons.
- Removed duplicates to maintain data integrity.
- Data Optimization:
- Created a Date Table in Power BI for efficient time-based analysis.
- Established relationships between tables (e.g.,
users
,orders
,order_items
,products
) to enable seamless data exploration.
Purpose: To analyze the distribution of customers across different countries, states, and cities, highlighting popular regions.
- Top States: Bar chart showing states with the highest number of visits.
- Most Visited Countries: Pie chart to display the share of each country.
- Most Visited Cities: List of cities with the highest visitor count.
- Map Visualization: Provides a geographical view of customer locations.
- Filters: Allows filtering by gender and date to view regional data for specific segments.
Purpose: To compare customer spending and behavior across genders.
- Total Spending by Gender: Bar chart comparing total sales by gender.
- Average Age by Gender: Line chart showing age trends for each gender over time.
- User Base by Age Group and Gender: Stacked area chart comparing age distribution across genders.
- Gender Distribution: Pie chart summarizing the gender split among customers.
- Table Summary: Shows breakdown of traffic sources by gender.
- Filters: Gender and country filters to refine the view.
![Sales Performance Dashboard]
Purpose: To analyze sales trends, top-performing products, and category performance.
- Top Products: Bar chart showing products with the highest sales.
- Sales by Category: Pie chart of sales contribution by product category.
- Sales by Day of Week: Bar chart showing sales volume on each day of the week.
- Key Metrics: KPIs displaying total sales, total orders, and average order value.
- Filters: Options to filter by order status, gender, and date.
![Traffic Source Analysis Dashboard]
Purpose: To identify which traffic sources bring in the most profitable and repeat customers.
- Total Sales per Traffic Source: Bar chart for revenue by traffic source.
- Repeat Customers by Traffic Source: Bar chart showing customer loyalty per source.
- Average Order Value by Traffic Source: Bar chart for average order size per source.
- Traffic by Gender: Pie chart showing the breakdown of traffic sources by gender.
- Detailed Table: Lists total sales and order counts by traffic source and country.
- Filters: Allows filtering by gender, order status, and date to understand the impact of traffic sources on different customer segments.
- Clone the Repository: Clone this repository to your local machine.
- Power BI File: Open
Ecommerce_Analysis.pbix
in Power BI Desktop to interact with the dashboards. - Dataset: If you want to explore further, you can access the dataset directly on BigQuery using the link provided above.
- Country Analysis: Helps identify key customer regions and potential areas for regional marketing.
- Gender Analysis: Highlights differences in spending and age demographics between male and female customers, aiding in gender-targeted campaigns.
- Sales Performance: Provides insights into top products, best-performing categories, and sales trends, supporting inventory and sales strategies.
- Traffic Source Analysis: Identifies the most profitable traffic sources and which sources bring in loyal, repeat customers, informing marketing budget allocation.
- Power BI File:
Ecommerce_Analysis.pbix
- The main Power BI dashboard file. - Screenshots: A folder containing screenshots for each dashboard (e.g.,
Country_Analysis.png
,Gender_Analysis.png
, etc.). - README.md: Project documentation explaining each dashboard and the analysis process.
Feel free to fork this project and submit pull requests if you’d like to contribute additional features, insights, or improvements.
This project is open-source and available under the MIT License.