Customer Retention and Predictive Analytics System
Ikram Aissiou
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.
Key Technologies:
Python (Machine Learning and Spatial Analysis)
Hybrid Recommendation Systems
PowerBI (Data Visualization)
SQL (Data Extraction and Analysis)
GIS tools (Geospatial Analysis)
Outcomes:
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
Like this project
Posted Sep 15, 2024
I developed a customer churn prediction system for a telecom company, enabling personalized retention strategies through a hybrid recommendation system.
