Superstore Sales and Profit Prediction Final Year Project with Source Code

• Admin login in this final year project
• Admin dashboard
• User management
• View registered users
• Manage user records
• Dataset cleanup
• Clean uploaded datasets
• Manage dataset records
• Support platform maintenance
• Monitor user and dataset activity

• User signup in this final year project
• User login
• User profile management
• Forgot password through email
• Forgot password through security question
• Update profile details
• Upload Superstore CSV dataset
• Select dataset versions
• Preview uploaded dataset
• Search dataset preview
• Sort dataset preview
• Clean missing values
• Remove duplicate records
• Format dataset columns
• Apply date range filter
• Apply region filter
• Apply state filter
• Apply city filter
• Apply category filter
• Use preset filters
• Train machine learning model
• Train Random Forest for sales prediction
• Train Random Forest for profit prediction
• Make single form-based prediction
• Upload CSV for bulk prediction
• View prediction result
• View top category insights
• View region summary
• View trend view
• View training history
• View prediction history
• Use sample Superstore dataset for testing

Dataset Management Features in this Final Year Project

• Upload CSV dataset
• Select dataset version
• Preview dataset records
• Search dataset records
• Sort dataset records
• Clean missing values
• Remove duplicate records
• Format column names

• Use sample dataset:

  sample_superstore.csv

• Upload sample dataset through Dataset section
• Prepare dataset for model training
• Store dataset version for later use

Data Cleaning Features in this Final Year Project

• Missing-value handling
• Duplicate record cleanup
• Column formatting
• Dataset validation
• Cleaned data preparation
• Dataset preview after cleanup
• User-controlled dataset selection
• Admin dataset cleanup support

Filter Features in this Final Year Project

The system supports business filters such as:

• Date range
• Region
• State
• City
• Category
• Preset filters
• Dataset-level filtered view
• Analysis-ready filtered records
• Prediction-ready filtered records

Machine Learning Features in this Final Year Project

• Sales prediction using machine learning
• Profit prediction using machine learning
• Random Forest model training
• Trains model from selected dataset
• Uses Superstore dataset features
• Supports single prediction
• Supports bulk prediction using CSV upload
• Stores model training history
• Stores prediction history
• Useful for business forecasting
• Suitable for sales analytics explanation
• Suitable for profit analytics explanation

Prediction Features in this Final Year Project

• Single form-based sales prediction
• Single form-based profit prediction
• Bulk CSV prediction upload
• View prediction output
• Store prediction result
• Review prediction history
• Compare prediction records
• Use trained model for future predictions

Insights Features in this Final Year Project

• Top categories analysis
• Region summary
• Trend view
• Sales insight generation
• Profit insight generation
• Dataset-based business analytics
• Report-ready insight output
• Useful for project report charts and explanation

Other Features in this Final Year Project

• Complete Superstore Sales and Profit Prediction source code
• Suitable for final year project, major project, and minor project
• Project report content can be prepared from included modules
• Flask web application
• User authentication
• Admin management
• Dataset upload
• Dataset preview
• Dataset cleaning
• Sales prediction
• Profit prediction
• Random Forest machine learning
• pandas data processing
• scikit-learn model training
• SQLite database
• Flask-Mail support
• Gmail forgot-password support
• Sample Superstore dataset support
• Training and prediction history
• Business insights module
• Useful for viva, source code review, project report writing, and project demonstration

1. Open terminal in the project folder:

   cd "superstore-sales-and-profit-prediction"

2. Create virtual environment:

   python -m venv venv

3. Activate virtual environment on Windows:

   venv\Scripts\activate

4. Install dependencies:

   pip install -r requirements.txt

5. Optional: configure forgot-password email using Gmail App Password.

6. Create .env file by copying:

   .env.example

7. Add mail credentials:

   [email protected]
   MAIL_PASSWORD=your-app-password

8. Initialize database and seed dummy data:

   python seed_data.py

9. Run the application:

   python app.py

10. Open project in browser:

http://localhost:5000

11. Upload sample dataset from Dataset section:

sample_superstore.csv

Admin Account

• Email: [email protected]
• Password: Admin@123

Demo User Account

• Email: [email protected]
• Password: User@123

Other dummy users:
Any seeded dummy user can be used with the default user password if available in the seed data.