I developed a predictive customer churn model with 90% accuracy for a telecommunications company, using machine learning to identify customers at risk of leaving. The system implemented proactive retention strategies, offering personalized recommendations to high-risk customers via a hybrid recommendation engine. I also conducted a spatial analysis across 39 regions to identify geographic factors influencing churn, such as network coverage and service quality. To monitor the impact of churn on business performance, I built a PowerBI dashboard and website, enabling the company to track churn rates and retention efforts in real-time. This comprehensive solution helped the company implement targeted retention strategies and address region-specific issues for improved customer satisfaction.

Python (Machine Learning and Spatial Analysis)

Hybrid Recommendation Systems

PowerBI (Data Visualization)

SQL (Data Extraction and Analysis)

GIS tools (Geospatial Analysis)

90% churn prediction accuracy

Increased customer retention through personalized offers

Identified state-level issues that required deeper analysis, including network coverage

Enhanced business decision-making with a PowerBI dashboard tracking churn and spatial analysis insights