Marcelo Seijas

Data-driven professional specializing in predictive analytics and business intelligence

MS

About Me

My background, education, and the skills that drive my work in data science

Background & Education

I'm a data-driven professional with a Master's in Data Science and Marketing Analytics and a Bachelor's in Economics and Business Economics, both from Erasmus University Rotterdam.

My professional experience spans client enablement, reporting automation, and strategic partner management, where I've successfully supported major consulting firms—including the Big Four—in adopting and integrating cloud-based reporting solutions. Passionate about bridging technical expertise and business insights, I'm transitioning towards roles that emphasize technical problem‑solving and data‑informed decision‑making.

My master's thesis involved leveraging predictive modeling and advanced text analytics on experimental reviews, focusing on robust pipeline deployment and comprehensive model evaluation.

Key Skills

Languages & Tools

PythonSQLPandasFastAPIGitDocker

Expertise

Machine LearningNLPAutomationData VisualizationDeployment

Featured Projects

Showcasing my work in data science, machine learning, and software development

Finance Integration Dashboard
Comprehensive Flask application for financial data analysis and visualization of coffee & beverage companies

Multi-source financial data platform with intelligent fallbacks (Finnhub → Yahoo Finance → Hardcoded), real-time stock tracking, sentiment analysis, and interactive Plotly dashboards. Features smart caching, background ETL pipelines, technical indicators, earnings analysis, and CSV export capabilities for coffee industry stocks.

FlaskPostgreSQLPlotlyPythonDockerAPIs
Coffee Text Analytics
Academic thesis project leveraging multi-modal text analysis and predictive modeling for consumer coffee reviews

Comprehensive thesis project implementing BERT embeddings, topic modeling, and ensemble methods to analyze consumer coffee reviews. Features MLflow experiment tracking, Optuna hyperparameter optimization and boosting techniques. Includes sophisticated feature engineering with TF-IDF, BERT embeddings, sentiment analysis, and topic modeling (LDA/NMF).

PythonBERTXGBoostMLflowOptunaNLP

Latest Articles

Insights and thoughts on data science, machine learning, and emerging technologies

June 2024
Using Python for Daily Automation

How I automated weekly reporting with Python, Pandas, and cron jobs to save hours of manual work every week.

PythonAutomationPandas
May 2024
Deploying a Streamlit App with Vercel

Lessons learned from pushing my first app into production, including deployment strategies and common pitfalls to avoid.

StreamlitDeploymentVercel
April 2024
Understanding CI/CD for Data Projects

My beginner take on setting up GitHub Actions for reproducible ML pipelines and automated testing workflows.

CI/CDGitHub ActionsMLOps

Resume

Download my comprehensive resume to learn more about my experience, education, and technical expertise

Professional Resume

Complete overview of my data science journey, technical skills, and project achievements

View Resume (PDF)

Get in Touch

Let's connect and discuss how data science can solve your business challenges

Let's Connect

I'm always interested in discussing new opportunities, collaborating on innovative projects, or sharing insights about data science and machine learning. Feel free to reach out!

Send a Message
Fill out the form below and I'll get back to you as soon as possible.