🛒 Retail Sales Forecasting & Inventory Optimization System

---

📌 Project Overview

This project presents an end-to-end Retail Analytics System that forecasts product demand and optimizes inventory decisions using Machine Learning and business logic.

It not only predicts future sales but also converts predictions into actionable inventory recommendations such as Safety Stock, Reorder Point (ROP), and Order Quantity.

---

🎯 Problem Statement

Retail businesses commonly face:

• ❌ Stockouts → Loss of revenue and customer dissatisfaction
• ❌ Overstocking → Increased holding costs and wastage

There is a need for a data-driven solution to balance supply and demand efficiently.

---

💡 Solution

This system provides:

• 📈 Sales Forecasting using Machine Learning

• 📊 Feature Engineering for time-series data

• 📦 Inventory Optimization:

  • Safety Stock
  • Reorder Point (ROP)
  • Order Quantity

• 🌐 Interactive Dashboard using Streamlit

---

🏢 Industry Relevance

This type of system is widely used by companies like Amazon, Flipkart, and Reliance Retail to:

• Improve demand planning
• Optimize inventory levels
• Reduce operational costs

---

⚙️ Tech Stack

• Python
• Pandas, NumPy
• Scikit-learn (Random Forest)
• Matplotlib, Seaborn
• Joblib
• Streamlit (Dashboard)

---

🧱 Project Architecture

Data → Preprocessing → Feature Engineering → Model → Forecast → Inventory Optimization → Dashboard

---

📁 Folder Structure

Retail-Sales-Forecasting-Inventory-Optimization/ │ ├── data/ # Raw & processed datasets ├── src/ # Core ML & processing scripts ├── models/ # Saved trained model ├── images/ # Graphs & screenshots ├── notebooks/ # Analysis notebook ├── app/ # Streamlit dashboard ├── main.py # Main execution script ├── requirements.txt # Dependencies └── README.md # Project documentation

---

🚀 How to Run the Project

1️⃣ Install Dependencies

pip install -r requirements.txt

---

2️⃣ Run Complete Pipeline

python src/generate_data.py python src/data_preprocessing.py python src/feature_engineering.py python src/model.py python main.py python src/visualization.py

---

3️⃣ Run Dashboard

streamlit run app/app.py

---

📊 Results & Outputs

📈 Sales Trend

📦 Promotion Impact

🤖 Model Performance (Actual vs Predicted)

🌐 Dashboard Output

---

📦 Inventory Optimization Output

The system calculates:

• Demand during Lead Time
• Safety Stock
• Reorder Point (ROP)
• Order Quantity

👉 Helps businesses make real-time inventory decisions.

---

🧠 Key Learnings

• Time-series forecasting techniques
• Feature engineering for temporal data
• Machine learning model development
• Inventory optimization concepts
• End-to-end project deployment

---

🔮 Future Improvements

• Multi-store & multi-product forecasting
• Real-time API integration
• Advanced models (XGBoost, Prophet)
• Automated replenishment system
• Cloud deployment

---

👩‍💻 Author

Vaishnava Devi

---

⭐ If you found this project useful, give it a star!