I am a Data Scientist with 5+ years of experience building production-grade machine learning and analytics systems across healthcare, IT services, and consulting environments.

I specialize in end-to-end ML ownership — from problem framing and hypothesis-driven analysis to model development, evaluation, deployment, and stakeholder adoption. My work focuses on converting complex, high-dimensional data (EHRs, behavioral signals, operational logs) into trustworthy, decision-ready insights with measurable business and clinical impact.

🩺 Predictive and causal modeling on large-scale longitudinal healthcare data
📈 Designing statistically rigorous ML pipelines aligned with real-world workflows
🔍 Building explainable & monitored ML systems for daily decision-making
📊 Translating models into executive dashboards and narratives

📐 Advanced statistical modeling & quasi-experimental methods
⏱️ Time-series modeling & forecasting for operational systems
🧪 Model calibration, diagnostics & evaluation in high-stakes settings
☁️ Scalable Python + SQL pipelines on cloud infrastructure

Data Scientist | Dec 2024 – Nov 2025

• Built and deployed statistical, causal, and ML models over 50K+ longitudinal EHR records, achieving ~20% PR-AUC improvement
• Led hypothesis-driven analyses and quasi-experiments using cohort analysis and EDA
• Owned pipelines end-to-end (SQL → Python → production) and presented insights to senior leadership

Machine Learning Engineer / Data Scientist | Sep 2021 – Jul 2023

• Developed risk prediction and prioritization models for high-volume operational workflows
• Applied forecasting, regression, and feature ablation to evaluate system changes
• Productionized ML solutions reducing reactive handling and improving proactive outcomes by ~30%

Junior Data Scientist / Data Science Intern | 2019 – 2021

• Applied ML and statistical techniques to customer and system-level data
• Built scalable SQL pipelines and analysis-ready datasets
• Delivered insights via dashboards and data stories influencing planning decisions

📊 Machine Learning & Statistics

• Classification, Regression, Tree-Based Models
• Time Series Modeling & Forecasting
• Model Calibration, Diagnostics, Statistical Analysis

☁️ Cloud & Distributed Systems

• AWS (EC2, S3), Spark, Distributed Data Processing

📈 Visualization & Reporting

• Tableau, Executive Dashboards, Stakeholder Reporting

⚙️ Engineering & Tooling

• REST APIs, CI/CD, Docker, Git, Agile/Scrum

This GitHub contains real-world, end-to-end ML projects focused on:

✅ Clear problem framing
✅ Reproducible data pipelines
✅ Interpretable model evaluation
✅ Business-aligned metrics & outcomes

📁 data/        → Sample or synthetic datasets
📁 notebooks/  → EDA & modeling
📁 src/        → Reusable pipeline code
📁 metrics/    → Evaluation & diagnostics
📄 README.md   → Problem, approach, results