🛒 Customer Shopping Behavior – Data Analytics Project
📌 Overview This project analyzes 3,900 real shopping transactions to understand customer behavior, spending trends, product preferences, and loyalty patterns. The end-to-end workflow includes Python-based EDA, SQL analysis in PostgreSQL, and an interactive Power BI dashboard to support business decision-making.
📂 Dataset Rows: 3,900 Columns: 18 Features include: demographics, purchase details, discounts, ratings, frequency, and subscription status Missing values: 37 ratings (imputed using median by category)
🛠 Tools Used Python (Pandas, NumPy, Visualization) MySQL (SQL queries & business insights) Power BI (dashboard & storytelling) Gamma (presentation)
🔍 Key Project Steps ✔ Data Cleaning & Preparation (Python) Loaded & explored data Standardized column names Created age groups & purchase frequency fields Removed redundancy between discount & promo fields Loaded cleaned data into PostgreSQL
✔ SQL Business Analysis Examples include:Revenue by gender Discount-driven high-spenders Top-rated products Shipping price comparison Subscriber vs non-subscriber revenue Discount-dependent products Customer segmentation (New / Returning / Loyal) Top 3 products per category Revenue by age group
✔ Dashboard in Power BI Interactive visuals showing: KPIs (customers, avg spend, avg rating) Sales & revenue by category Subscription impact Age-group performance Shipping preferences
📈 Key Insights Loyal customers form the majority of revenue Express shipping users spend slightly more Some products rely heavily on discounts Young adults contribute the highest revenue Higher purchase frequency links to subscriptions
💡 Business Recommendations Strengthen loyalty programs Promote subscription benefits Optimize discount strategy Highlight top-rated products Target high-revenue age groups
👤 Author Aditya Ranjan // Linkedln - www.linkedin.com/in/aditya-ranjan-3bab11248