Built an end-to-end churn analytics solution to analyze historical customer behavior and predict future churners using SQL, Power BI, and Machine Learning. 1) Designed complete ETL pipeline in Microsoft SQL Server for data cleaning and transformation 2) Developed interactive executive dashboard in Microsoft Power BI with KPI tracking (Total Customers, Churn Rate, New Joiners) 3) Implemented Random Forest model in Python using scikit-learn to predict high-risk customers 4) Identified key churn drivers including contract type, tenure, payment method, and service usage Outcome: Enabled proactive identification of at-risk customers and supported data-driven retention strategy.