I am an End-to-End Data Analyst & Analytics Developer specializing in data pipeline engineering, web scraping automation, and predictive modeling. I build robust data architectures—from raw web data collection to advanced machine learning deployments—to solve complex business problems.

🌐 Languages: Portuguese (Native) | English (Advanced/Fluent)
📬 Contact: marcosscatolino@gmail.com | LinkedIn

• Data Engineering & Automation: Web Scraping (Selenium, BeautifulSoup), ETL/ELT Pipelines, Data Automation
• Data Analysis & Machine Learning: Python (Pandas, NumPy, Scikit-Learn, Matplotlib, Seaborn), Predictive Modeling, Demand Forecasting, Exploratory Data Analysis (EDA)
• Database Management: Advanced SQL (Full Stack: Database Creation, Schema Design, Relationships, Complex Queries, Joins, Aggregations)
• Data Visualization & Web Apps: Streamlit, Tableau

An end-to-end machine learning pipeline focused on the logistics and e-commerce sector using public data.

• The Problem: E-commerce and logistics companies lose customer retention due to unmapped, systemic public complaints.
• The Solution: Built a complete data pipeline that ingests public complaint data, processes text, and applies Machine Learning models using Scikit-Learn to predict patterns and categorize bottlenecks in the supply chain.
• Tech Stack: Python, Scikit-Learn, Pandas, Matplotlib, Seaborn.

Automated data extraction system designed to bypass manual data gathering and build custom datasets.

• The Problem: Lack of structured market data available via traditional APIs.
• The Solution: Developed autonomous scripts capable of navigating complex web pages, handling dynamic content, and extracting clean data into relational formats.
• Tech Stack: Python, Selenium, BeautifulSoup.

Profissional de Dados focado no ciclo completo da informação: desde a captura automatizada via Web Scraping, modelagem de bancos de dados relacionais em SQL, até a criação de pipelines de dados e modelos preditivos com Machine Learning. Transformo dados brutos em inteligência estratégica e automação de alto impacto.

• Engenharia de Dados & Automação: Web Scraping (Selenium, BeautifulSoup), Pipelines ETL/ELT, Automação de Processos.
• Análise de Dados & Machine Learning: Python (Pandas, NumPy, Scikit-Learn, Matplotlib, Seaborn), Modelagem Preditiva, Previsão de Demanda, Análise Exploratória (EDA).
• Bancos de Dados: SQL Avançado (Criação, Modelagem de Esquemas, Relacionamentos, Consultas Complexas, Joins, Agregações).
• Visualização de Dados: Streamlit, Tableau.