Hello, I'm

Juan Daniel
Hernandez Vargas

Data Scientist & Specialization Candidate

Providing advanced statistical modeling and data-driven solutions for the Banking and Fintech sectors.

Juan Daniel Hernandez Vargas

About Me

Juan Hernandez

My Journey

I am a Data Scientist currently completing a professional specialization in Statistical Analytics. My background in Biology provided me with a strong investigative foundation, which I now apply to the complex data architectures of the financial world.

I focus on bridging the gap between raw data and strategic decision-making, specifically within Risk Analysis for the Banking and Fintech sectors. I specialize in developing explainable models that reveal the "why" behind behavioral and financial trends.

Beyond my technical pursuits, I am a dedicated problem solver who enjoys diving into data patterns to mitigate risk and optimize ROI in high-stakes environments.

Σ

Statistical Analysis

Specialized in probability, regression, and hypothesis testing.

🤖

Machine Learning

Predictive modeling focusing on Churn and Risk Analytics.

🏛️

Fintech & Banking

Data-driven solutions specifically for the financial sector.

📊

Explainable AI

Decoding complex models using SHAP for business transparency.

My Resume

My Professional Resume

Data Scientist specializing in Statistical Analytics & Risk Management for the Banking and Fintech sectors.

Featured Projects

Drag or scroll to explore →

Model Performance Chart
Fintech · Risk Analytics

Customer Churn Prediction & Explainable AI

Beta Bank

Business Impact

Identified high-risk segments — older, inactive clients in Germany — enabling targeted retention campaigns. Random Forest + SMOTE delivered the best balance of precision and recall.

F1 Score 0.62
AUC-ROC 0.86
Models 3
Python Random Forest SHAP Scikit-Learn SMOTE
View Case Study →
Credit Model Performance
Fintech · Credit Risk

Credit Origination Model & Vendor Benchmarking

Solventa — Technical Assessment

Business Impact

Full credit scoring pipeline with OOT validation, SHAP audit, and ethical AI analysis. Compared Gender-inclusive vs Gender-blind models — only 0.96 pp GINI loss for a fairer system. Neither external vendor outperformed the internal model.

AUC-ROC 0.627
GINI 25.3%
Validation OOT
LightGBM Optuna SHAP Scikit-Learn SciPy
View Case Study →
Insurtech · Colombia

Vehicle Insurance Claims — EDA

Fasecolda SOAT Data

Objective

Exploratory analysis of Colombia's mandatory vehicle insurance (SOAT) claims — accident frequency, claim severity, and regional patterns across departments.

In Development
Python Pandas Matplotlib
Fintech · Colombia

Financial Inclusion Gap Analysis

Banca de las Oportunidades

Objective

Statistical testing of Colombia's financial inclusion data — evaluating whether rural location and income level are significant predictors of being unbanked.

Upcoming — Phase 2
Python SciPy Hypothesis Testing
Fintech · Colombia

SME Credit Risk — Informal Economy

DANE Encuesta de Micronegocios

Objective

Classification model predicting which informal Colombian businesses are likely to access formal credit — directly relevant to fintech lending and financial inclusion.

Upcoming — Phase 3
Python XGBoost Scikit-Learn SHAP

Technical Expertise

Proficient Intermediate
💻

Core Tech & Languages

Python SQL (PostgreSQL) R Studio Advanced Excel Pandas / NumPy
🤖

Data Science & ML

Scikit-Learn Machine Learning Churn Prediction XGBoost / Random Forest SHAP (Explainable AI)
📊

Statistical Analytics

Hypothesis Testing Probability Distributions Linear & Logistic Regression Time Series Forecasting Multivariate Analysis
🏛️

BI & Risk Tools

Power BI Tableau Risk Analysis Data Visualization GitHub / Git

Get In Touch

Let's build something data-driven together.

I am currently open to new opportunities in Data Science and Risk Analysis within the Banking and Fintech sectors. Whether you have a specific inquiry or just want to connect, I'd love to hear from you.