Building reliable data systems, interpretable machine learning models, and responsible AI systems.
I work at the intersection of data science, machine learning, and data engineering, with a focus on building systems that are reliable, interpretable, reproducible, and useful in practice.
My projects span the data lifecycle — from data ingestion and validation to feature engineering, predictive modeling, explainability, and deployment. More recently, I have been exploring AI-agent security and data provenance, particularly how untrusted information propagates through autonomous systems and how runtime policies can make those systems safer.
|
Provenance-aware runtime security for AI agents Explores how untrusted information can be tracked through agent workflows and incorporated into deterministic security decisions.
Core idea
|
End-to-end machine learning system Production-oriented ML project covering feature engineering, model comparison, explainability, experiment tracking, model serving, and testing.
Pipeline
|
|
Applied data science for operational risk Transforms supply-chain and operational data into structured signals for risk analysis and decision support.
Pipeline
|
Healthcare data engineering pipeline Focuses on ingestion, validation, transformation, and data-quality workflows for provider data.
Pipeline
|
|
Machine learning for predictive risk Investigates patterns associated with fraudulent behavior and develops predictive models for risk estimation.
|
Behavioral modeling and customer analytics Examines customer behavior, develops predictive features, and models factors associated with churn.
|
Statistical Learning · Data-Centric ML · Explainable AI · ML Systems · Responsible AI · AI Agent Security
I am particularly interested in model reliability, data quality, interpretability, provenance, and the behavior of machine learning systems beyond model training.
| Programming | Python · SQL |
| Data | Pandas · NumPy · ETL · Data Validation · Feature Engineering |
| Machine Learning | Scikit-learn · XGBoost · LightGBM · Model Evaluation |
| Explainability | SHAP · Feature Analysis · Model Interpretation |
| ML Engineering | FastAPI · MLflow · Docker · REST APIs · Model Serving |
| Analytics | Power BI · Excel · Exploratory Data Analysis · Visualization |