I transform data into valuable insights through statistical analysis, machine learning and data visualization to support strategic decisions.
Get to know my journey and experience
I'm a Data Scientist passionate about discovering patterns and hidden insights in data. With experience in statistical analysis, machine learning and data visualization, I work to transform raw data into strategic information.
My approach combines scientific rigor with creativity to solve complex problems and generate real value for organizations through data-driven solutions.
My journey and key accomplishments
Tools and platforms I master
How I interact with technologies in my daily work
Validations of my technical competencies
Automatically synced from Credly
Demonstration of technical rigor and production
5 main projects that demonstrate technical rigor, reproducibility, and production focus
Complete data processing system with DataOps pipeline that integrates Python and MongoDB, offering full support for local, remote, and Docker environments with advanced ETL/ELT features.
git clone https://github.com/alex-des-santos/Case-Engenheiro-dadosdocker-compose up -dpython main.py
Executive dashboard for data governance and strategic KPIs, with modern lakehouse architecture and automated ETL/ELT pipeline for decisions based on reliable data.
git clone https://github.com/alex-des-santos/kpis-governance-dashboardnpm install or pip install -r requirements.txt
Executive dashboard for financial analysis of Adventure Works with revenue forecasts using Machine Learning and market opportunity analysis.
Interactive web tool that uses generative AI for automatic analysis of CSV files, generating statistical insights, visualizations, and recommendations in real time.
End-to-end Machine Learning production pipeline with experiment tracking (MLflow), inference API (FastAPI), and containerized infrastructure. Wine quality classification with 88% F1 Score.
git clone https://github.com/alex-des-santos/ml-production-pipelinedocker compose up -ddocker exec ml-api python3 train.pylocalhost:5000 and API at localhost:8001/docs
Open guide to build a Data Science portfolio with checklists, templates, and practical references.
Study crossing habits and performance of students using notebooks, visualizations, and statistical experiments.
Engine that compares job openings with CVs, suggests improvements, and feeds the official Chrome extension for automated optimization.
Interactive educational platform to teach machine learning concepts through dynamic visualizations and accessible practical examples.
Modern and intuitive web tool for analyzing Windows Event Viewer logs, with intelligent insights generated by AI using Google Gemini for automatic identification of critical issues.
Complete Machine Learning pipeline from training to production: tracking with MLflow, REST API with FastAPI, Docker containerization, automated CI/CD and data drift monitoring.
Modern lakehouse architecture: public data ingestion → dbt (staging/intermediate/marts) → Great Expectations for data quality → versioned metrics → executive dashboard with BI.
RAG system for technical documentation with traceable citations, automated evaluation (RAGAS), security hardening (prompt injection), complete telemetry and regression tests.
Complete list of my own repositories (no forks) focused on AI, data, automation, and productivity.
Repository
24/7 multi-agent orchestrator that triages tickets autonomously with LangGraph/LangChain state machines.
Open on GitHubRepository
Interactive README that highlights mission, principles, and professional roadmap.
Open on GitHubRepository
Research that connects students' habits and performance using notebooks, visualizations, and statistical experiments.
Open on GitHubRepository
Adventure Works executive dashboard with forecasting, What-If analysis, and Brazil-specific storyline.
Open on GitHubRepository
DataOps challenge with Python + MongoDB pipelines, Dockerized environments, and full operational docs.
Open on GitHubRepository
Browser-based CSV analyzer that produces instant statistics and D3.js charts for huge files.
Open on GitHubRepository
Plotly Dash dashboard that cross-analyzes deforestation, fire spots, and rainfall across Brazilian biomes.
Open on GitHubRepository
Open guide to build a compelling data science portfolio with checklists, templates, and curated references.
Open on GitHubRepository
Pandemic impact analysis on ENCCEJA results combining public datasets and notebook storytelling.
Open on GitHubRepository
End-to-end data governance case with strategic KPIs, architecture diagrams, and BI deliverables.
Open on GitHubRepository
Visual playground that explains ML algorithms with interactive demos and intuitive charts.
Open on GitHubRepository
Interactive guide that walks home users through network diagnostics via dynamic Q&A flows.
Open on GitHubRepository
Streamlit app that breaks long Stable Diffusion/ComfyUI prompts into reusable sections for faster iteration.
Open on GitHubRepository
Engine behind the AI Resume Optimizer that compares job posts vs. CVs and powers the Chrome extension.
Open on GitHubRepository
Automated Dungeon Master for WhatsApp that manages sheets, dice rolls, and full D&D storytelling with AI.
Open on GitHubRepository
Web tool that interprets Windows Event Viewer logs, flags critical signals with AI, and speeds up troubleshooting.
Open on GitHubGet in touch for discussions about projects and opportunities