Pavan Kumar Settineni

About Pavan Kumar Settineni

Data Analyst with 5+ years of experience delivering high-impact analytics solutions across healthcare and financial services. I specialize in transforming complex, high-volume data into actionable insights that improve operational efficiency, reduce risk, and drive measurable business outcomes. In my current role, I built a patient risk-scoring system that reduced 30-day hospital readmissions by 18% and improved care prioritization. Previously, I developed fraud detection models that increased detection accuracy by 25% while reducing false positives through data-driven experimentation and A/B testing. I bring strong expertise in SQL, Python (Pandas, Scikit-learn), and cloud-based data platforms including Snowflake, Redshift, and Azure. I have hands-on experience building scalable ETL pipelines, optimizing data workflows, and designing dashboards in Tableau and Power BI that enable stakeholders to make faster, data-informed decisions. My strength lies in working across the full data lifecycle—from data extraction and transformation to modeling and visualization—while bridging the gap between technical teams and business stakeholders. I’m currently seeking opportunities where I can contribute to building robust data systems, delivering advanced analytics, and driving strategic impact in data-driven organizations.

Experience

1. Data Analyst

   Kaiser Permanente

   Jan 2025 — Present · CA, US

   Built a patient risk-scoring solution on clinical and demographic data that cut 30-day hospital readmissions by 18%, helping the department avoid roughly $150K in annual penalty costs.• Ran the analytics project lifecycle on Waterfall — requirements, milestones, and clinical-stakeholder reviews — delivering all planned releases on time across 2 project cycles.• Pulled healthcare data through PostgreSQL and wired ingestion via Azure Data Factory and Blob Storage, reliablyprocessing 50K+ patient records per batch with no data-loss incidents.• Cleaned and standardized patient datasets in Python and NumPy using SSIS and Alteryx, cutting data-prep time by 35% and freeing roughly 8 analyst hours per week.• Ran EDA in Seaborn on demographics and medical history, identifying 10+ high-signal features that lifted model accuracy by 8% over baseline.• Trained Python regression models to flag high-risk patients, lifting readmission prediction accuracy by 22% and helping care teams prioritize early interventions.• Designed Tableau dashboards tracking patient risk scores and readmission trends, improving reporting turnaround by 25% for a team of clinical leads and care managers.• Automated patient-data summaries with Azure OpenAI, cutting manual reporting effort by roughly a third so care teams could review risk patterns same-day.

Education

• California State University - East Bay

  Master of Science - MS, Statistics with a specialization in Data Science

• Jawaharlal Nehru Technological University Kakinada (JNTUK)

  Bachelor of Technology - BTech, Electronics and communication engineering