juan daniel hernandez vargas

I’m a results-driven Data Scientist with a strong statistical foundation and a professional certification in Data Science. I build end-to-end machine learning solutions and automate complex workflows using Python and SQL.

I specialize in risk assessment and user behavior prediction, particularly within fintech, insurance, and biotech contexts. I’ve delivered models such as LightGBM, XGBoost, and Random Forest to uncover actionable drivers behind churn and operational outcomes.

I focus on performance that matters: improving predictive accuracy while making insights usable. Through deployments like interactive Streamlit dashboards and KPI visualizations (e.g., SHAP and confusion matrices), I translate model outputs into measurable business strategies.

My professional ethos is grounded in research-grade rigor—hypothesis testing, bootstrapping, and operational risk analysis—so decisions are backed by quantified uncertainty and clear probabilities of loss.