About me

I am a Principal Data Scientist at QuantumBlack, and I work and live in London. I’m using this site to occasionally share some of my personal insights and opinions about the world of data science.

I graduated with distinction from the University of Oxford with a masters degree in statistics. Before moving to the fields of statistics and data science, I was mainly interested in stochastic calculus, numerical methods and financial mathematics. I have a BSc degree in Applied Mathematics with distinction from Delft University of Technology, in which I focused heavily on these subjects.

If you want to get in touch with me, you can contact me by email, or through my LinkedIn page. I’m always happy to connect with other people that share my interests.

Talks

• No more grid search! How to build models effectively at London AI meetup in August 2019.
• Injury prediction in elite sports at Data Science Croatia meetup in May 2019.
• Why giving your algorithm ALL THE FEATURES does not always work at PyData London 2018.
• Bayesian optimisation with scikit-learn at PyData London 2017.

Papers

• Huijskens, T. P., Ruijter, M. J., & Oosterlee, C. W. (2016). Efficient numerical Fourier methods for coupled forward–backward SDEs. Journal of Computational and Applied Mathematics, 296, 593-612. Preprint here.

Open-source

• stability-selection: an implementation of the stability selection algorithm, compatible with the scikit-learn API and part of scikit-learn-contrib.
• scikit-hyperband: an implementation of the hyperband algorithm for hyper-parameter optimisation, compatible with the scikit-learn API.