nagul = {
    "name"        : "Nagul Meera Shaik",
    "role"        : "Financial Analyst @ JPMorgan Chase & Co.",
    "location"    : "USA 🗽 — Open to Relocate Anywhere in the USA",
    "education"   : "MS Data Science — Pace University, New York (2024)",
    "focus"       : ["FP&A", "Financial Modeling", "Risk Analytics", "Data Engineering"],
    "certifications": ["Microsoft Power BI", "Tableau Desktop Certified Professional"],
    "work_modes"  : ["Onsite", "Hybrid", "Remote"],
    "passion"     : "Transforming complex financial data into strategic business insights"
}

• 🏦 Currently building real-time financial analytics platforms at JPMorgan Chase & Co.
• 📊 4+ years across Finance, Business Intelligence, and Data Analytics
• 🤖 Building AI-powered forecasting models with ARIMA, Prophet & XGBoost
• ⚡ Delivered 14% forecast accuracy improvement and 30% reduction in reporting cycle time
• 🔍 Validated 2M+ financial records for SOX compliance at Epsilon
• 🎓 MS in Data Science from Pace University, New York

🟢 Actively seeking opportunities | Available immediately | Open to relocate anywhere in the USA | Onsite · Hybrid · Remote

Apache Kafka · Python · Scikit-Learn · Snowflake · Ensemble ML

A streaming fraud detection system processing transactions in near real-time using an ensemble of Z-Score, IQR, and Isolation Forest detectors. Multi-channel alerts (Email, Slack, SNS) with deduplication and rate limiting.

✅ <100ms alert latency via Kafka streaming    ✅ 3-model ensemble (Z-Score + IQR + IForest)
✅ 6 financial compliance rules enforced       ✅ Multi-channel alerting with deduplication

AWS Glue · Amazon S3 · Snowflake · dbt · Power BI

Production-grade ELT platform processing 500K+ financial transactions daily across Bronze → Silver → Gold medallion layers. Includes 15+ automated data quality checks and 50+ financial KPI marts.

✅ 70% reduction in manual reporting cycle     ✅ 15+ DQ checks automated
✅ Bronze / Silver / Gold medallion architecture  ✅ 50+ financial KPIs via dbt

Python · ARIMA · Prophet · XGBoost · AWS Lambda · Power BI

Ensemble forecasting engine combining ARIMA + Facebook Prophet for 12-month revenue projections with 14% accuracy uplift. Serverless AWS Lambda pipeline auto-refreshes forecasts monthly.

✅ 14% forecast accuracy improvement           ✅ Serverless auto-refresh via AWS Lambda
✅ ARIMA + Prophet ensemble model              ✅ Confidence intervals & scenario analysis

AWS S3 · AWS Glue · Snowflake · dbt · Power BI

End-to-end cloud finance pipeline with Star Schema design delivering 50+ financial metrics. Fully automated ELT workflow from raw S3 data to analytics-ready Snowflake warehouse.

✅ Star schema data warehouse design           ✅ 50+ financial metrics automated
✅ AWS S3 + Glue + Snowflake stack             ✅ parquet-optimized storage layer

Python · XGBoost · MLflow · FastAPI · scikit-learn

End-to-end fraud detection pipeline achieving AUC 0.916 using XGBoost with MLflow experiment tracking and FastAPI deployment. Production-ready ML serving layer with model versioning.

✅ AUC 0.916 fraud detection accuracy          ✅ MLflow experiment tracking & model registry
✅ FastAPI REST endpoint for real-time scoring ✅ Full ML pipeline from raw data to deployment

Python · scikit-learn · SQL · Power BI

ML-powered churn prediction model for U.S. insurance clients achieving 81% accuracy with 21% revenue uplift potential. Integrated Power BI dashboard for business stakeholder review.

✅ 81% model accuracy on insurance churn       ✅ 21% revenue uplift potential identified
✅ Python + scikit-learn + SQL pipeline        ✅ Power BI executive dashboard

Python · SQL · Pandas · yfinance · Power BI

Comprehensive S&P 500 market analysis using Python and SQL with Power BI visualization. Covers market trend identification, sector performance, and portfolio analytics.

✅ S&P 500 full market data analysis           ✅ Sector-level performance breakdown
✅ yfinance API integration                    ✅ Power BI interactive dashboard

Python · Jupyter Notebook · Machine Learning

End-to-end analysis of telecom customer churn patterns using ML classification models to identify at-risk customers and recommend retention strategies.