I'm an Assistant Professor of Economics transitioning into a data science career. My background is in international trade and applied econometrics, with extensive experience in empirical modeling, causal inference, and working with large-scale structured datasets.

Over the past two years I’ve built a portfolio of Python, SQL, and R projects that apply machine learning, causal inference, and financial data analysis to real-world problems. My work now includes production-ready, end-to-end pipelines using modern MLOps tools.

• Shipment Prediction Pipeline
  End-to-end machine learning pipeline for predicting late shipments using public retailer order data.
  Tools: Python, scikit-learn, FastAPI, Docker, AWS (ECS, ECR, S3, IAM, CloudWatch), MLflow, Prefect, CI/CD (GitHub Actions)
  Metrics: 92.1% accuracy and 97.3% recall across two optimized Random Forest models

• Financial Data Pipeline and KPI Analysis
  Automated ingestion and storage of company financials from the Alpha Vantage API with SQL querying and Python visualization.
  Tools: Python, SQL (SQLite), requests, pandas, matplotlib, seaborn

• Causal Impact of the EU–Ukraine FTA
  Empirical evaluation of trade agreement effects using a dynamic gravity model.
  Tools: R (tidyverse, ggplot2), econometric modeling, causal inference

Languages & Tools: Python, SQL, R, Git/GitHub, Jupyter, Stata
Libraries: pandas, scikit-learn, NumPy, matplotlib, seaborn, requests, BeautifulSoup, joblib
MLOps & Deployment: FastAPI, Docker, MLflow, Prefect, AWS (ECS, ECR, S3, IAM, CloudWatch), CI/CD with GitHub Actions
Core Areas: Machine Learning, Causal Inference, Data Wrangling, Econometric Modeling, Data Visualization

For academic publications and teaching, visit my research website.