Freelance Data Scientist & Analytics Expert | Tom Rooijakkers | Data Ilumina | Landing Page | English Version

Tom Rooijakkers

 




  Fulltime on project until May 2026; trainings possible.

About Me

Nice to meet you!


Profile picture
Hi, I'm Tom - a Freelance Data Scientist with a passion for uncovering patterns and solving real-world challenges. From a young age, I've been fascinated by maps, puzzles, and making sense of complexity. Now I apply that same curiosity to my work in data.
With 7+ years of experience in the following sectors, I love tackling diverse challenges:
  • Energy
  • Tech
  • Water Management
  • Recruitment
  • R&D
I also enjoy exploring new industries, connecting ideas across disciplines, and uncovering insights others might miss.
My core expertise spans:
  • Machine Learning
  • Data Science & Engineering
  • Geospatial Analytics
I hold the following diplomas:
  • MSc Energy Science, Utrecht University (cum laude)
  • BSc Earth Sciences, Utrecht University (Honours)
These are the certifications I currently hold:
  • Certified Analytics Professional - Expert (CAP-X)
  • AWS Certified Machine Learning - Specialty (MLS-C01)
  • Databricks Certified Data Engineer Associate
  • Certified Microsoft Azure Data Fundamentals (DP-900)
I excel in translating complex data into actionable strategies that drive real-world results, combining the capability of deep analysis with a practical mindset.
Looking for a fresh, cross-disciplinary perspective on your data? Let's connect!

Services

Consulting | Analytics Translation

I bridge the gap between business needs and data solutions to enable data-driven decision-making across industries.

Machine Learning & AI Solutions

I design and deploy advanced Machine Learning models that reveal patterns, predict outcomes, and transform processes at scale.

Python Development | Web Apps

I specialize in Python development, crafting data-driven apps, automating workflows, building robust pipelines and full-stack (Flask) web solutions.

Cloud Solutions | Data Engineering

I design and implement scalable cloud architectures and data pipelines, leveraging AWS, Azure, and Databricks for seamless data operations.

Visualization | Geo | Advanced Analytics

I turn complex data into visually compelling insights using advanced geospatial and data visualization techniques.

Data Training, Education & Coaching

I offer tailored training and coaching on Data Science, Python, Cloud, and Data Engineering to empower teams and professionals.

Certifications

The certifications below showcase my expertise and my commitment to continuous learning:

 

  • Certified Analytics Professional - Expert (CAP-X)

    • Bridging the gap between data and business impact

    The CAP-X certification demonstrates my expertise in the full analytics lifecycle, from framing business problems to delivering actionable insights. This means I can help you turn raw data into strategic decisions that drive measurable outcomes.

     

  • AWS Certified Machine Learning - Specialty (MLS-C01)

    • Building scalable AI solutions in the cloud

    Holding this certification, I specialize in designing, training, and deploying Machine Learning models on AWS. Whether you need automated ML workflows, scalable inference, or cloud-native AI solutions, I provide cost-effective deployment using industry best-practices.

     

  • Databricks Certified Data Engineer Associate

    • Optimizing big data pipelines & analytics

    I am certified in building and managing scalable data pipelines on Databricks, using Spark, Delta Lake, and advanced ETL techniques. If you need robust data engineering solutions, I can help design and implement efficient architectures for analytics and Machine Learning.

     

  • Microsoft Azure Data Fundamentals (DP-900)

    • Laying the foundation for cloud-driven analytics

    This certification ensures a solid understanding of Azure's data ecosystem. I can help optimize storage, improve query performance, and enable real-time business intelligence, allowing your business to make data-driven decisions with confidence.

     



Skills

Python
Machine Learning & AI Algorithms
Data Visualization
Geospatial Analysis
Data Engineering & Cloud
Business Intelligence

Tech Stack & Tools

This tech stack highlights the core tools I use to solve complex challenges and deliver results:

    Programming & Scripting

  • Python
  • SQL
  • JavaScript
  • Bash

 

    Data Science & Machine Learning

  • Pandas
  • NumPy
  • Scikit-Learn
  • Keras
  • TensorFlow
  • PyTorch
  • XGBoost

 

    Cloud & Big Data

  • Amazon Web Services (AWS): S3, Lambda, SageMaker
  • Azure: Data Factory, Synapse
  • Spark: Apache Spark, PySpark
  • Databricks
  • Delta Tables
  • Data Lakehouse

 

    Geospatial Analysis

  • GeoPandas
  • RasterIO
  • QGIS
  • Folium

 

    Data Visualization & BI

  • Matplotlib
  • D3.js
  • Seaborn
  • Plotly
  • Leaflet
  • Power BI

 

    DevOps & Workflow Automation

  • GIT: GitHub, GitLab, Azure DevOps
  • CI/CD
  • Selenium
  • Multiprocessing

 

    Methodologies:

  • Design Thinking
  • Agile
  • Scrum
  • (Advanced) Energy Modeling
  • Functional Design (business requirements to Features and User Stories)

 

    Other:

  • Flask
  • REST APIs
  • Timeseries Analysis
  • Web Scraping / Data Mining

 

Portfolio

A collection of projects demonstrating my expertise in Data Science, Machine Learning, and data visualization. Click on the images for more details.

  • All
  • Projects
  • Apps
  • Blogs

Loading Water Monitoring Data in Bulk (Flask)

Enabling non-coders to use large timeseries datasets.

KNMI Weather Data Analysis (GitHub)

Exploring weather data to identify trends and anomalies.

Automated Talent Matching

Machine Learning-based text classification in recruiting.

Data Science Use Case Selection & Implementation

Identifying and delivering Data Science use cases in Water Management.

Residential Solar Energy & Shade Modeling

Python-based photovoltaic (PV) shade study resulting in a publication.

SharePoint File Handling (Azure Databricks)

Custom PySpark script to handle file transfers in the cloud.

Clustering Similar Groundwater Sites (SOM)

Using Self-Organizing Maps to quantify groundwater site similarity.

Anomaly Detection from Timeseries Statistics

A straightforward approach to improve timeseries data quality.

Contact

Let's connect! Fill in the form below to get in touch. You can also mail me directly or leave a message on LinkedIn.


Note: JavaScript must be enabled for the form below to work correctly. Rest assured: this is fully the case if you can see more than just plain text on this page.

Location

Utrecht, Netherlands

I am available to work remotely worldwide, on-site or hybrid within NL, and hybrid abroad (up to 2 - 3 consecutive days per week).

Call Me

Available on request

Email Me

contact[at]datailumina[dot]com

GDPR Agreement

Loading
Your message has been sent. You will hear from me soon. Thank you!