Available for work · Lisbon, PT

Samuel
Garcia.

Seven years in finance. Now building ML systems that actually ship — from S&P 500 forecasting to Fed sentiment models.

Machine Learning Finance → ML Python / PyTorch NLP / MLOps
Scroll
01 — Projects

Work that
ships.

ML / Finance · 01
Macro-Alpha Engine
S&P 500 Forecasting
Featured · Live
Macro-Alpha Engine
End-to-end S&P 500 forecasting system combining macro indicators with XGBoost and LSTM models. Live dashboard with real-time signal generation and SHAP explainability.
PythonXGBoostLSTMSHAPDocker
View Live →
ML / Fintech · 02
Fraud Detection ML System
Real-Time Transaction Scoring
Fintech · Live
Fraud Detection ML System
Cost-aware fraud classification on 500K+ transactions. XGBoost + Isolation Forest ensemble with SHAP per-transaction explanations and an analyst-facing dashboard.
PythonXGBoostSHAPStreamlitDocker
View Live →
Quant / Trading · 03
Algo Trading Gold Bot
Gold Strategy · Backtesting
Quant · Live
Algo Trading Gold Bot
Systematic gold trading strategy with walk-forward backtesting, Sharpe / max drawdown reporting, and a live performance dashboard.
PythonBacktraderPandasPlotlyStreamlit
View Live →

The story
so far.

I spent seven years in financial services and banking operations before pivoting into machine learning. That background isn't a detour; it's the whole point. I build models that solve real problems in domains where the stakes are high and the data is messy.

Right now I focus on production ML: forecasting systems, NLP pipelines, and tools that go from notebook to deployment. Based in Lisbon, open to opportunities.

Samuel Garcia

The tools
I reach for.

From model training and evaluation to deployment and domain-specific data — the full picture of what I work with day-to-day.
Core ML
Python
PyTorch
XGBoost
Scikit-learn
SHAP
MLflow
Data & Visualisation
Pandas
NumPy
SQL
Plotly
Streamlit
Infrastructure
Docker
GitHub Actions
Linux / CLI
Finance Domain
Derivatives
Risk Analytics
Econometrics
Time Series
NLP / Sentiment
P&L Reconciliation
Financial Modelling
05 — What's next

Further project
planning.

A running list of ideas, experiments, and things in the pipeline — from new ML projects to tools I'm building for myself.

View Roadmap →
06 — Contact

Let's build
something.

Open to freelance projects, full-time roles, and interesting conversations. Based in Lisbon — available globally.

[email protected]
LinkedIn GitHub Email