Data-Driven Retail Inventory Optimization | RetailIQ Analytics Platform

This project presents a complete data analytics and decision-support system for the retail industry. The goal is to transform raw sales data into meaningful insights, accurate forecasts, and smart inventory decisions. 🔍 What this project covers: - Exploratory Data Analysis (EDA) with 25+ visualizations - Interactive dashboard with 10 tabs and real-time filters - Sales forecasting using Prophet model - Inventory optimization using Safety Stock, Reorder Point (ROP), and EOQ - Risk classification for better stock management 🛠️ Tools & Technologies Used: - Python (Pandas, NumPy, Matplotlib, Seaborn) - Prophet for time series forecasting - Jupyter Notebook & VS Code - Excel/CSV dataset - Custom RetailIQ Dashboard 📈 Key Features: - KPI cards for revenue, transactions, and performance tracking - City-wise, product-wise, and customer behavior analysis - Forecast accuracy of 85.8% (above industry benchmark) - Smart inventory recommendations to avoid stockouts 🎯 Outcome: This system helps businesses: - Make data-driven decisions - Predict future demand - Optimize inventory efficiently 🚀 Future Enhancements: - CSV upload for dynamic analysis - Advanced models like LSTM & ARIMA - Real-time data integration - Automated stock alerts 👩‍💻 Project By: Harshitha H M Lakshmi B C Sinchana M Mouneshwari S P 🎓 GM University, Davanagere Project Based Learning (PBL) --- #DataAnalytics #RetailAnalytics #PythonProject #EDA #Forecasting #InventoryManagement #MachineLearning #StudentProject