Chandra Challa

Data Analyst @Blue Cross Blue Shield Association

TX, US

Extracted, cleaned, and standardized large-scale pharmacy and eligibility datasets from Oracle and PostgreSQL using Python (Pandas, NumPy) to support analytics use cases including formulary adherence, refill gap detection, and utilization review. Delivered high-quality, analytics-ready datasets for care managers and pharmacists.Built and maintained automated ETL pipelines using Informatica and Apache Airflow, integrating claims, EMR, and member interaction data across 7+ healthcare systems. Reduced manual reconciliation efforts by 35% and improved reporting timeliness for compliance audits.Designed secure, HIPAA-compliant data lake architecture on AWS S3 integrated with AWS Glue Catalog, enabling governed, schema-aware storage for structured and unstructured healthcare data.Developed predictive ML models using Scikit-learn to forecast emergency department visits and inpatient admissions, enabling proactive care interventions that reduced preventable hospitalizations.Designed and deployed executive-level dashboards in Tableau to monitor cost trends, medication adherence, and risk-adjusted outcome measures, driving data-informed decision-making.Optimized large-scale data pipelines in Snowflake and PostgreSQL using partitioning, clustering, and indexing techniques to improve performance and scalability.Managed version-controlled repositories using GitLab and PyCharm, ensuring reproducible workflows, clean documentation, and effective cross-functional collaboration.Partnered with compliance, actuarial, and clinical stakeholders in Agile/Scrum environments (Rally) to translate business requirements into technical solutions aligned with HIPAA and CMS standards.Conducted statistical hypothesis testing (p-values, significance analysis) on clinical intervention outcomes while ensuring PHI anonymization and adherence to federal data governance policies.

University of North Texas

Master's degree, Data Analytics