Data
Analyst.
Building pharmacy analytics pipelines, data governance frameworks, and BI dashboards that drive measurable outcomes across Healthcare & Financial Services.
// what I've built
Featured Projects
Specialty Pharmacy Claims Analytics
PostgreSQL • Python ETL • Streamlit • Plotly
End-to-end SP claims pipeline on 2,000 specialty pharmacy claims across 10 drugs and 7 payers. Full PostgreSQL schema with ER model, PL/pgSQL audit triggers, 11 KPI SQL queries, and 5-tab Streamlit executive dashboard.
Drug Utilization & Formulary Analytics
MySQL • Python ETL • Streamlit • Prior Auth
Formulary tier management and drug utilization analytics on 5,000 Rx across 20 drugs. MySQL schema with stored procedure, 2,047 prior auth requests analyzed, generic substitution opportunity engine estimating plan savings.
Healthcare Data Quality & Governance
PostgreSQL • Rules Engine • Audit Trail • Streamlit
Enterprise DQ pipeline with 21 configurable validation rules across 4 clinical datasets. Severity-weighted scoring, column-level data profiling, reconciliation reporting, downstream impact registry tracking 7 reports, and full audit log.
Pharmacy Readmission Risk Predictor
XGBoost • scikit-learn • MLflow • CCI • Streamlit
30-day readmission risk prediction on 2,500 patients using Charlson Comorbidity Index (CCI) scoring, pharmacy features, and lab values. Logistic Regression achieved ROC-AUC of 0.8432. Interactive CCI calculator for real-time risk scoring.
Pharmacy Supply Chain & Prescription Analytics
PostgreSQL • Oracle SQL • Python ETL • Streamlit
End-to-end pharmacy supply chain platform covering drug inventory management, supplier performance, prescription fill rates, stockout analysis, and automated reorder alerts.
Financial Risk Dashboard
PostgreSQL • Python • XGBoost • Streamlit
End-to-end credit risk analytics pipeline on 2.26M Lending Club loans ($34B portfolio). XGBoost default prediction model achieving AUC-ROC of 0.73. Interactive Streamlit dashboard with real-time filters deployed publicly.
Earnings Call NLP Analyzer
FinBERT • HuggingFace • Python • Streamlit
FinBERT sentiment analysis on 514 earnings call transcripts from 30 S&P 500 companies across 8 sectors. Detected COVID-19 impact (Disney Q3 2020 negative sentiment) and identified risk language patterns.
Retail Demand Forecasting
Python • ARIMA • Prophet • XGBoost • MLflow
End-to-end demand forecasting pipeline on real Walmart weekly sales data. XGBoost achieved 2.61% MAPE — 74% below the industry benchmark of 5–10%. Includes promotional uplift modeling and MLflow experiment tracking.
Customer Churn Prediction
Python • Scikit-learn • XGBoost • Random Forest • MLflow
ML classification project predicting telecom customer churn on 7,043 real customers. Logistic Regression achieved best ROC-AUC of 84.60% with recall of 78.61% — correctly identifying 4 out of 5 at-risk customers.
U.S. Maternal Mortality Analysis
Python • Tableau • Excel • CDC Data • PRAMS
M.S. capstone project analyzing the impact of COVID-19 on U.S. maternal mortality rates (2017–2023). MMR rose 51% during the pandemic (25.91 → 39.26). Adj. R²=0.941 between mortality ratio and year.
SQL Analytics & dbt Project
SQL • dbt • Snowflake • Data Modeling
End-to-end analytics engineering project using dbt + SQL to build modular data models, tests, and documentation on a real business dataset. Targeting banking and retail analytics use cases.
// where I've worked
Professional Journey
Data Analyst
- Built time-series and ML forecasting models to predict customer behavioral trends, supporting demand planning and business forecasting use cases.
- Improved data accuracy by 22% through automated SQL + Python validation pipelines on Snowflake enterprise data warehouses.
- Designed Tableau self-service dashboards driving a 35% increase in digital banking adoption and 14% improvement in customer satisfaction.
- Applied feature engineering and model validation contributing to 20% improvement in customer follow-up efficiency.
Data Analyst
- Delivered consulting engagements for healthcare and pharmacy clients, collaborating with clinical SMEs and IT teams to gather requirements and translate operational needs into scalable data solutions.
- Extracted, transformed, and validated large-scale EHR and pharmacy datasets using SQL and Python, reducing missing records by 18% through automated validation and reconciliation pipelines.
- Developed risk stratification models using logistic regression and the Charlson Comorbidity Index (CCI), contributing to a 22% reduction in 30-day readmissions.
- Designed interactive Power BI dashboards and automated ETL pipelines; commissioned and decommissioned datasets in alignment with governance requirements.
- Supported data governance including metadata management, normalization, and standardization; documented ETL processes in Confluence for audit readiness.
Technical Arsenal
Languages & Querying
BI & Reporting
Analytics & ML
Data Engineering
Healthcare & Pharmacy
Governance & Tools
Education
University of North Carolina at Charlotte
M.S. Health Informatics and Analytics
Koneru Lakshmaiah University
Bachelor of Pharmacy
Certifications
Let's build something together.
Actively targeting Senior Data Analyst roles across the United States — open to Healthcare, Pharma, and Financial Services.