Machine Learning

Retail Sales Prediction Using Machine Learning

The Retail Sales Prediction Using Machine Learning system is a comprehensive machine learning solution that predicts retail sales using the Superstore Sales Dataset. This project is ideal for B.Tech, MCA, CSE, and engineering students as their final year project. It implements XGBoost and Random Forest with feature engineering, achieving 89.23% R² accuracy and 42.15 RMSE.

The system utilizes the Superstore Sales Dataset containing 9,994 records with 21 features including product categories, customer segments, order dates, and shipping information. It provides a user-friendly web interface for data upload, exploratory data analysis, model training, and real-time sales prediction, enabling retailers to optimize inventory management, promotional planning, and revenue forecasting.

• Multi-Model Sales Prediction
• XGBoost (R²: 0.8923)
• Random Forest (R²: 0.8756)
• Feature Engineering (temporal features, shipping duration)
• 5-Fold Cross-Validation
• Interactive Visualizations
• Real-time Sales Predictions
• Model Performance Comparison
• Feature Importance Analysis
• Flask Web Application