This project demonstrates how to combine multiple data sources
into a unified dataset, perform data cleaning and exploratory analysis
in SQL, and build interactive dashboards in PowerBI to derive business insights.
Customer churn poses a major challenge for subscription-based companies. Retaining existing customers is often more cost-effective than acquiring new ones, making churn prediction a valuable business strategy. This project aims to predict customer churn and identify the key drivers of attrition, using a combination of SQL and Python for data analysis and machine learning.
In today’s competitive e-commerce landscape, data-driven strategies are essential for understanding customer behavior, optimizing inventory, and maximizing revenue. This project focuses on analyzing online retail sales data to uncover key business insights and support strategic decision-making. By combining data preprocessing in Python with powerful visualizations in Tableau, the goal is to identify what drives sales, when and where performance peaks, and who the most valuable customers are.