sushmitha = {
"name" : "Sushmitha Kokkalgave",
"role" : "Senior Data Analyst | BI Engineer | Healthcare Analytics",
"location" : "New Jersey, USA 🇺🇸",
"email" : "susmitha.data97@gmail.com",
"education" : "M.S. Computer & Information Science — Florida Atlantic University (2024)",
"currently" : "Data Analyst @ United Health Group — analyzing 50M+ member records",
"building" : ["End-to-end ETL pipelines", "KPI dashboards", "Predictive models"],
"learning" : ["MLOps", "Advanced Databricks", "dbt (data build tool)"],
"collab" : "Healthcare analytics, data engineering & BI projects",
"achievements": {
"cost_savings" : "$2M+ identified through trend modeling",
"data_accuracy" : "99.8% across enterprise reporting systems",
"reporting_time" : "~60% reduction via automated dashboards",
"forecast_gain" : "~25% improvement in prediction accuracy",
"records_analyzed": "50M+ member records at United Health Group",
},
"superpower" : "Turning raw, messy data into executive-ready KPIs that drive decisions",
"fun_fact" : "I built a data quality framework that catches errors before humans do ✨",
}
| 🏥 United Health Group | 📊 BI & Reporting | 🔧 Engineering | 🎓 Education |
|---|---|---|---|
| 50M+ records analysed | 15+ exec dashboards built | 99.8% data accuracy | M.S. CIS — FAU 2024 |
| $2M+ cost savings found | ~60% reporting time saved | 40% ETL efficiency gain | AWS · GCP · Azure certified |
| ~25% forecast improvement | 100+ SQL queries automated | 4hrs → 30min extraction | 9 active certifications |
SQL & Data Querying ████████████████████░ 98% ▸ Expert
Python (Pandas/NumPy) ████████████████████░ 95% ▸ Expert
ETL / Data Pipelines ███████████████████░░ 92% ▸ Expert
Power BI / Tableau ███████████████████░░ 90% ▸ Advanced
Cloud (AWS/Azure/GCP) █████████████████░░░░ 85% ▸ Advanced
PySpark / Databricks ████████████████░░░░░ 82% ▸ Advanced
Predictive Modeling ███████████████░░░░░░ 78% ▸ Proficient
Apache Airflow ██████████████░░░░░░░ 72% ▸ Proficient
| 🏷️ Project | 📝 Description | 🔧 Stack | 🔗 Links |
|---|---|---|---|
| 🔓 Insights Unlocked Pro | End-to-end ETL pipeline surfacing business KPIs from multi-source data | Python SQL Databricks PySpark |
Repo → |
| 🏥 Healthcare Claims Pipeline | Full claims analytics pipeline — 7 KPI categories, Power BI dashboards | Python PySpark AWS S3 Azure |
Repo → · Dashboard → |
| 📈 Revenue Forecasting & Variance | ML pipeline — LR + XGBoost forecasting, budget variance detection, anomaly flags | Python XGBoost Snowflake Tableau |
Repo → · Dashboard → |
| ✅ Data Quality Monitoring | Automated DQ framework — 6 check types, Airflow DAG, alerting, 0–100 quality score | Python Airflow PostgreSQL Azure |
Repo → · Dashboard → |
"Turning 50 million data points into decisions that matter — one pipeline at a time."
— Sushmitha Kokkalgave
— Sushmitha Kokkalgave