Data Scientist at CBZ Holdings

Developed a customer segmentation model analyzing transaction patterns across 500K+ customers to enable targeted marketing campaigns and improve retention. Built a predictive credit risk model (Random Forest, XGBoost) to assess default probability, reducing portfolio risk and improving loan approval accuracy by 25%. Deployed a real-time fraud detection system using ensemble techniques, cutting fraudulent transactions and strengthening security. Implemented automated ETL pipelines and a scalable data warehouse (PostgreSQL), enabling near real-time analytics for leadership. Created interactive Power BI dashboards tracking 15+ KPIs across units to guide strategic planning. Performed geospatial analyses to identify growth opportunities in underserved markets supporting branch and ATM network optimization.