About me

I enjoy combining applied mathematics and software development for engineering and data science applications. I have been fortunate enough to build on all of these passions as a Senior Data Scientist at Dexcom and in my prior positions as a Data Scientist at Our Community and as a PhD student at The Univeristy of Melbourne. I developed my passion for data science by working as a Data Analyst for a Dutch railway company, analyzing sensor and contractor data. I founded and co-organized the Melbourne Datathon which attracted 120 data enthusiasts in the first year, over 300 in the second year, over 500 in our 2017 edition, and has since grown even further.

• Cum laude BSc and MSc in Applied Mathematics from The Delft University of Technology, with a focus on scientific computing.
• PhD from The University of Melbourne, applying machine learning and graph-theoretical techniques to fluid flow and heat transfer granular, porous media.
• Research internships at Schlumberger, IBM and for a small energy consultant (Alboran), where I learned how to connect, communicate and collaborate.
• Data analytics experience at Keyrail (railway operator), working with sensor data, performance data and dashboards.
• Data science experience at Our Community (software company and social enterprise), performing predictive modeling, time series analysis, AB experiments, text analytics, survey analysis, dashboard design & more.
• Currently, I am a Sr. Data Scientist at Dexcom (healthcare technology), where I mainly focuss on retention and churn models.

Ask me about

• Data science for fundraising activities (research on donations and grants)
• The bias trade-off for algorithmic decision making (white paper)
• Transitioning from student to data scientist (talk)
• Organising a hackathon for data science (blog and video)
• Complex networks and machine learning (journal paper)
• Numerical linear solvers and preconditioning (journal paper and MSc thesis)

Click on a skill to read more about my experience, or show all / close all .

• Python
  5 years experience with data analysis. Used in various research- and business-projects for data tidying, data visualization, statistical analyses, machine learning, graph analytics, information retrieval. Libraries: numpy, scipy, pandas, scikit-learn, networkx, matplotlib, seaborn, rpy2. Tools: Jupyter, Spyder, regular expressions.
  
  
• SQL
  2 years experience with data extraction. Used on daily basis, both in small-data (<10GB) and big-data (10TB+) settings. Tools: BigQuery, postgreSQL, pgAdmin.
  
  
• C++
  4 years experience with high-performance applications. Used in various research projects for advanced numerical (solver, preconditioning) algorithms, basic graph search algorithms, computational geometry and parallel computation. Libraries: STL, CGAL, OpenCV, OpenMP, MPI. Tools: Sublime, Visual Studio, Xcode, CMake.
  
  
• Cloud computing
  2 years experience. Near-daily use of the Google Cloud Platform, including BigQuery, Compute Engine, Cloud Storage and the AI Platform. Also operationalized a text classifier using AWS Lambda.
  
  
• Matlab
  7 years experience with quick implementations and prototyping. Used throughout education for linear algebra and numerical analysis.
  
  
• VBA
  3 years experience with Excel integration. Used to build various data dashboards, and to perform automated reporting and data management.
  
  
• Other
  Java: undergraduate subject. R: explored graphical models for PhD research and did some forecasting. D3.js: developed a few visualizations, including a scroller. Spark: online introductory courses on edX. HTML/Jekyll/Markdown: this website. Unix: bash, compilation. Photoshop, iMovie: image/video editing. Comsol: physics simulations during PhD. Paraview: physics visualizations during PhD. Simpleware ScanFE: finite element meshing.
  
  

  ---