Financial Crime & Data Analyst based in Bogotá, Colombia. I specialize in turning operational and transactional data into actionable insights for fraud detection, AML compliance, and business intelligence.
Currently transitioning from workforce management analytics into fintech and financial crime analytics, combining 3+ years of hands-on data work with a Data Science specialization from 4Geeks Academy.
FinCrime Transaction Monitor — End-to-end fraud detection system simulating transaction monitoring for neobank AML compliance.
XGBoost classifier · 11 engineered features mapped to AML typologies · PR-AUC 0.68 · Precision 65.7% · Recall 67.4% · Interactive Streamlit dashboard for compliance analysts
Python XGBoost scikit-learn Streamlit Plotly pandas
Languages: Python, SQL
Data & Analytics: pandas, numpy, Power BI, Looker Studio, Excel (advanced)
Machine Learning: scikit-learn, XGBoost, feature engineering, classification, time series (ARIMA, Prophet)
Tools: Streamlit, Jupyter, Git, Genesys Cloud CX, Google Sheets
| Project | Description | Stack |
|---|---|---|
| FinCrime Transaction Monitor | Fraud detection pipeline with XGBoost + Streamlit dashboard | Python, XGBoost, Streamlit |
Open to roles in Financial Crime Analytics, Data Analytics (fintech), and AML/Compliance. English C1.