I am a Data Scientist specializing in Machine Learning, with a strong focus on anomaly detection and scoring. My goal is to help businesses leverage the power of their data to enhance decision-making and automate processes.

With a background in industrial engineering and teaching, I have developed a rigorous approach to data, the ability to explain complex concepts clearly, and expertise in cloud tools for deploying models into production.

🔹 Machine Learning (Scikit-learn, XGBoost, TensorFlow, PyTorch)
🔹 Data Engineering (SQL, BigQuery, dbt, dlt, Kestra)
🔹 MLOps & Cloud Computing (AWS, GCP, Docker, Kubernetes)
🔹 Development & Automation (Python, FastAPI, Flask)
🔹 Data Visualization & Storytelling (Matplotlib, Seaborn, Streamlit, Looker Studio)

🌟 Industrial Equipment Failure Prediction
➡️ Predicting industrial equipment failures with a machine learning pipeline, deployed on AWS Elastic Beanstalk.

🌟 Financial Distress Prediction
➡️ Classification model for predicting corporate bankruptcies, with a Flask API and cloud deployment.

🌟 OptiFund: Data-Driven Portfolio Optimization
➡️ A full-stack data engineering project using Kestra, GCS, and BigQuery to ingest and transform global stock indices. Business dashboards built in Looker Studio to compare performance and correlations.

✅ Machine Learning Zoomcamp - DataTalksClub
✅ Data Engineering Zoomcamp - DataTalksClub
✅ Data Scientist - OpenClassrooms/CentraleSupélec
✅ Publications & Sharing on LinkedIn about Machine Learning, Data Engineering, and MLOps

💡 Always looking for new challenges in data science and data engineering! Feel free to explore my projects and reach out.