Data Analyst / July, 2024 — Present

Designed and maintained 10+ interactive Power BI dashboards integrating SAP Epic and internal claims data sources to track patient risk KPIs care coordination metrics and compliance SLAs enabling real-time executive decision-making across 5+ stakeholder teams. Engineered end-to-end ETL pipelines using SQL Server and Python (Pandas) to extract cleanse and transform multi-million row healthcare datasets improving data reliability and reducing manual data preparation time by 35%. Performed advanced statistical analysis and built predictive analytics models (regression classification) in Python to support AI-driven patient risk scoring boosting model precision by 17% and reducing manual clinical review efforts by 30%. Conducted in-depth cohort analysis and root cause analysis using SQL (CTEs window functions) on claims and patient outcome data to identify care gaps improving care intervention accuracy by 12% and accelerating outcome reporting by 15%. Performed cost-benefit and ROI analysis using SQL and Excel to evaluate process improvements and predictive risk scoring tools delivering data-backed executive presentations that reduced processing delays by 25%. Developed and maintained a requirements traceability matrix tracking 100+ data and system requirements in Jira ensuring analytical deliverables met business objectives and audit compliance standards. Established data governance standards within SQL Server and SAP environments defining data validation rules quality checks and standardization protocols across global healthcare analytics teams. Collaborated with data science and product teams to define 15+ analytical use cases and KPI frameworks translating business questions into data models and measurable metrics that drove 20% efficiency gains.

Data Analyst / January, 2021 — July, 2023

Built and automated Tableau and Excel dashboards for financial operations teams tracking 20+ KPIs across digital lending and credit portfolios; reduced manual reporting turnaround by 30% and improved data accuracy for monthly business reviews. Wrote complex SQL queries (joins subqueries CTEs window functions) across SQL Server and Oracle databases on 500K+ record datasets to support root cause analysis loan performance monitoring and regulatory data validation. Performed exploratory data analysis (EDA) and data profiling using Python (Pandas Matplotlib Seaborn) to identify data quality issues anomalies and trends across borrower repayment and transaction datasets. Designed star schema data models and wrote ETL logic to consolidate loan origination credit scoring and customer onboarding data from multiple sources into a centralized reporting layer improving cross-team data consistency by 25%. Partnered with compliance and audit teams to produce regulatory data reports aligned with PCI DSS Basel III and SOX requirements supporting zero-defect audit outcomes and ensuring data lineage documentation was audit-ready. Leveraged AWS S3 and Lambda for data ingestion pipelines and contributed to cloud-based data workflows via AWS CodePipeline ensuring 90% on-time delivery of reporting milestones. Created data dictionaries SOPs and documentation for all analytical models and reporting processes in Confluence and SharePoint enabling knowledge transfer and consistent data usage across 3 regional teams. Conducted AB analysis and trend analysis on customer behavior and loan repayment patterns providing actionable insights to business stakeholders that informed credit policy revisions and reduced default risk exposure.