Myntra E-Commerce Sales Data Analytics Final Year Project with Source Code

Project Features in this Final Year Project

• Myntra-style e-commerce sales data analysis
• Financial year 2025–26 order analytics
• CSV dataset loading
• Data cleaning and preparation
• Order date parsing
• Invalid date row handling
• Discount column renaming
• Numeric column conversion
• Revenue column creation from final price
• Month and year extraction
• YearMonth feature creation
• Exploratory data analysis
• Dataset shape summary
• Date range summary
• Data type inspection
• Missing-value inspection
• Duplicate count checking
• Numeric summary statistics
• Categorical unique count analysis
• Revenue by category analysis
• 12 visualization chart generation
• Machine learning regression model
• Machine learning classification model
• ML metrics report generation
• Feature importance analysis
• PNG chart export
• Text-based ML report export

Data Analytics / EDA Features in this Final Year Project

• Reads:

  myntra_style_sales_dataset.csv

• Cleans column names
• Parses Order_Date as datetime
• Drops invalid date rows
• Converts quantity, age, MRP, discount, and final price into usable numeric fields
• Creates Revenue from Final_Price
• Creates month-wise trend features
• Prints dataset shape
• Prints date range
• Prints data types
• Prints missing-value summary
• Prints duplicate count
• Prints describe() summary for key numeric columns
• Prints unique counts for categorical fields
• Prints revenue by category
• Supports project report-ready EDA explanation

Visualization Features in this Final Year Project

The project generates 12 PNG charts in the outputs/ folder:

1. Monthly revenue trend
   File: 01_monthly_revenue_trend.png
   Chart type: Line chart
   Shows total revenue by month.
2. Revenue by category
   File: 02_revenue_by_category.png
   Chart type: Horizontal bar chart
   Shows revenue comparison across Men, Women, and Kids categories.
3. Top brands by revenue
   File: 03_top_brands_revenue.png
   Chart type: Horizontal bar chart
   Shows top 12 brands based on revenue.
4. Gender distribution
   File: 04_gender_distribution.png
   Chart type: Pie chart
   Shows order share by customer gender.
5. Payment mode orders
   File: 05_payment_mode_orders.png
   Chart type: Vertical bar chart
   Shows order count by payment method.
6. Top states by revenue
   File: 06_top_states_revenue.png
   Chart type: Horizontal bar chart
   Shows top 15 states by sales revenue.
7. Age histogram
   File: 07_age_histogram.png
   Chart type: Histogram
   Shows distribution of customer age.
8. Discount distribution
   File: 08_discount_distribution.png
   Chart type: Histogram
   Shows distribution of discount percentage.
9. Correlation heatmap
   File: 09_correlation_heatmap.png
   Chart type: Heatmap
   Shows correlation among Age, Quantity, MRP, Discount, and Revenue.
10. Revenue boxplot by category
    File: 10_revenue_boxplot_by_category.png
    Chart type: Box plot
    Shows revenue spread within each category.
11. Product type orders vs revenue
    File: 11_product_type_orders_vs_revenue.png
    Chart type: Grouped bar chart
    Shows normalized order count and normalized revenue for top product types.
12. MRP vs revenue scatter
    File: 12_mrp_vs_revenue_scatter.png
    Chart type: Scatter plot
    Shows MRP vs revenue by discount band.

Machine Learning Features in this Final Year Project

1. Revenue Prediction

• Uses Random Forest Regressor
• Predicts order-line revenue

• Target variable:

  Revenue / Final_Price

• Uses customer and basket composition features
• Excludes MRP and discount from revenue regression to avoid overly direct price-rule prediction
• Uses numeric and categorical preprocessing
• Uses train-test split
• Evaluates model using:
  • MAE
  • RMSE
  • R² score

• Saves top feature importances in:

  outputs/ml_model_report.txt

Features used for regression:

• Gender
• Age
• Brand
• Category
• Product_Type
• Size
• Quantity
• Payment_Mode

2. Category Classification in this Final Year Project

• Uses Random Forest Classifier

• Predicts product category:

  Men / Women / Kids

• Uses stratified train-test split
• Uses class balancing
• Evaluates model using:
  • Accuracy
  • Classification report
  • Precision
  • Recall
  • F1-score

Features used for classification:

• Gender
• Age
• Brand
• Product_Type
• Size
• Quantity
• MRP
• Discount_pct

Dataset Details in this Final Year Project

Dataset file:

myntra_style_sales_dataset.csv

Dataset type:
Synthetic / Myntra-style e-commerce fashion order dataset

Expected columns:

• Order_ID
• Order_Date
• Customer_ID
• Gender
• Age
• City
• State
• Brand
• Category
• Product_Type
• Size
• Quantity
• MRP
• Discount (%)
• Final_Price
• Payment_Mode

Derived columns created by script:

• YearMonth
• Month
• Year
• Revenue
• Discount_pct

Files / Modules Included

• myntra_sales_analysis.py — main Python program
• myntra_style_sales_dataset.csv — required input dataset
• requirements.txt — Python dependency list
• README.md — project documentation
• outputs/ — generated chart and ML report folder
• outputs/ml_model_report.txt — machine learning metrics and classification report

Output Files in this Final Year Project

The project generates all outputs inside:

outputs/

Expected output files:

• 01_monthly_revenue_trend.png
• 02_revenue_by_category.png
• 03_top_brands_revenue.png
• 04_gender_distribution.png
• 05_payment_mode_orders.png
• 06_top_states_revenue.png
• 07_age_histogram.png
• 08_discount_distribution.png
• 09_correlation_heatmap.png
• 10_revenue_boxplot_by_category.png
• 11_product_type_orders_vs_revenue.png
• 12_mrp_vs_revenue_scatter.png
• ml_model_report.txt

• Open terminal in the project folder:

  cd "Myntra Sales Data Analytics"

• Create virtual environment on Windows:

  python -m venv .venv
  .\.venv\Scripts\Activate.ps1

• Create virtual environment on macOS/Linux:

  python3 -m venv .venv
  source .venv/bin/activate

• Install dependencies:

  pip install -r requirements.txt

• Ensure dataset is available in the same folder as the script:

  myntra_style_sales_dataset.csv

• Run the analysis:

  python myntra_sales_analysis.py

• Check generated charts and ML report:

  outputs/

This project has no login credentials because it is not a web application.

Credential note:
No admin panel, user login, password, or database authentication is included. The project runs locally as a Python data analysis script