Pascal Van Kooten
Software Engineer at Van Kooten AI Solutions / ex-mgnr
Utrecht, Utrecht, Netherlands
Summary
🤩
Rockstar🎓
Top SchoolPascal Van Kooten is a software engineer and data scientist with 11 years of experience applying machine learning, statistics and full-stack development across finance, consulting and product projects. He combines a formal MSc in Methods and Statistics of Behavioral Sciences with hands-on roles from quantitative trading R&D to freelance AI work, delivering production systems and training teams in NLP and ML. Pascal actively contributes to open source—authoring projects like a neural-network autocomplete for code and a WiFi-based location predictor—and bridges model development with API and front-end integration. Competitive by nature, he has a strong track record in ML competitions and public speaking, and enjoys building prototypes that augment human capabilities. Currently Amsterdam-based, he is open to freelance engagements focused on prototyping, advisory work and data analysis.
11 years of coding experience
8 years of employment as a software developer
Sydney AcademyMaster of Science (MSc), Methods and Statistics of Behavorial Sciences, Master of Science (MSc), Methods and Statistics of Behavorial Sciences at University of Utrecht
English, Dutch
Stackoverflow
21,027reputation
5.9mreached
329answers
316questions
gmail
top-5%
r
top-5%
smtp
top-5%
python
top-5%
emacs
top-5%
Github Skills (32)
python10
apidoc10
scikit10
autocomplete10
machine-learning10
flask-ask10
e-mail10
api10
scikit-learn10
neural-network10
flask10
random-forest-classifier9
r9
digit9
cross-platform9
Programming languages (26)
Github contributions (5)
kootenpv/neural_complete
Jan 2017 - Dec 2020
A neural network trained to help writing neural network code using autocomplete
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:1 review, 22 commits, 3 PRs in 3 years 11 months
Contributions summary:Pascal contributed to the development of a neural network-based autocomplete system. Their work included implementing and modifying the server-side code, primarily written in Python, to handle prediction requests. They also focused on model management, incorporating changes to the training process, and integrating the model with a Flask-based API. Further contributions involved adding an Angular front-end component to interact with the backend.
neural-networkautocomplete
kootenpv/whereami
Sep 2016 - Jun 2018
Uses WiFi signals :signal_strength: and machine learning to predict where you are
Role in this project:Full-stack Developer
Full-stack DeveloperContributions:75 commits, 11 PRs, 68 pushes in 1 year 9 months
Contributions summary:Pascal primarily contributed to the development of the `whereami` project, which leverages WiFi signals and machine learning for location prediction. Their contributions involved installing dependencies, fixing bugs, and improving the application's API. They also updated the README, implemented features, and refactored existing code. The user further added support for cross-platform use and for the project's integration with the `access_points` library.
signalwifi-signalmachine-learningpredictdistance
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.