After a 5 year career in the sustainabiltiy & ESG domain, I'm transitioning to a role in in data science & analytics for a variety of industries.
I started my career as a sustainability analyst, with a degree in environmental science and a drive to make a difference. But along the way, I discovered something unexpected: a love for data. What began with simple Excel templates soon grew into a keen interest in coding and data visualization. I excel at asking insightful questions and using structured problem-solving, clean code and easy to read visuals to answer them.
I'm happiest when I can apply my knack for data-driven analysis and problem-solving together with writing. With 5+ years of experience in sustainability analytics, focusing on carbon emissions and climate policy, I’ve seen firsthand how communicating data simply and effectively can make or break the power of a story.
Now, with a Master's degree in Data Science from Tilburg University, I’m eager to bring my analytical skills to new domains. Beyond sustainability, I’m excited to apply my skills in Python, SQL, Power BI, machine learning and data engineering to solving problems and generating insights in sectors such as marketing, HR & people analytics, operations, supply chain and public policy analysis.
🔎 Here you can see some of the projects I've completed to demonstrate my skillset in:
- Querying, cleaning and transforming data using Python & SQL
- Data visualization using libraries like matplotlib and seaborn
- Data modeling & dashboarding using Power BI
- Building machine learning models using scikit-learn
- Designing data pipelines
| Project Link | Tools & Libraries | Domain | Methods | Description |
|---|---|---|---|---|
| 🎯📈 Customer segmentation & predicting subscriber churn | Python (scikit-learn, pandas, seaborn) | Marketing | Segmentation, machine learning | Using clustering and classification algorithms to identify subscriber personas and churn risk factors for targeted marketing campaigns |
| 📦📊 Inventory management with SQL | PostgreSQL | Supply chain & Logistics | Exploratory analysis | A SQL script exploring and aggregating inventory and order data for a wholesale food company |
| 🎓Graduation thesis: Semi-supervised text classification of manufacturing error messages | Python (scikit-learn, pandas, seaborn) | Manufacturing | Machine learning, Natural language processing | Designed and programmed a machine learning pipeline using both label propagation through clustering and semi-supervised classification algorithms |
| 🚓🕵️ Dutch crime data: national, regional and urban trends | Python (pandas, numpy, seaborn) | Public policy | Data storytelling | Calculates, visualizes and draws conclusions on total and violent crime rates per 1000 people for different geographic levels of the Netherlands from 2012 - 2024 |
| 🏘️ Rental revenue prediction with machine learning | Python (pandas, numpy, scikit-learn, seaborn) | Real Estate | Machine learning | Predict the revenue of rental properties using feature selection and hyperparameter tuning for various machine learning models |
| 🌍 Company GHG emissions time series construction | Python (pandas, numpy, matplotlib, scipy) | Sustainability / ESG | Time series analysis | Python script to construct emissions pathways based on company emissions data |