Philipp Probst
Data Scientist Und Aktuar
Zürich Metropolitan Area Switzerland
Summary
🤩
Rockstar🎓
Top SchoolPhilipp Probst is a data scientist and actuary with 11 years of experience, currently shaping motor insurance pricing at Allianz Suisse from his base in the Zürich metropolitan area. He holds a PhD in statistics from LMU Munich and specializes in tree-based and ensemble machine learning methods, hyperparameter tuning, multitarget and multilabel problems, and computational aspects of ML. As a long-term contributor to the influential mlr-org machine learning toolkit, he has improved testing, multilabel functionality, and performance evaluation routines used by the R community. His background spans applied industry work—from predictive maintenance research at Dräger to credit model validation—and hands-on statistical software development in R, Python and more. Colleagues know him for combining rigorous academic training with pragmatic, production-focused solutions and a persistent attention to model evaluation and reliability.
10 years of coding experience
2 years of employment as a software developer
Ludwig Maximilian University of MunichMaster of Science (MS), Statistik, Master of Science (MS), Statistik at Technische Universität Dortmund
German, English, Spanish, Portuguese, French
Stackoverflow
668reputation
35kreached
29answers
0questions
Github Skills (13)
machine-learning10
mlr10
r10
testing10
data-science9
classification9
multiclass-classification6
cox-regression6
auc6
random-forest6
python6
plotly6
hyperparameters6
Programming languages (8)
Github contributions (5)
mlr-org/mlr
Jul 2015 - Jun 2019
Machine Learning in R
Role in this project:
Data Scientist
Data ScientistContributions:47 commits, 42 PRs, 128 pushes in 3 years 11 months
Contributions summary:Philipp primarily contributed to the mlr-org/mlr repository by expanding the testing framework and adding functionality related to multi-label classification. Their work includes adding new tests, expanding existing ones to cover a wider range of scenarios, and implementing performance evaluations, specifically focusing on the integration of the getMultilabelBinaryPerformances function. Furthermore, they modified existing code to address potential issues with various prediction types, especially involving probability calculations for classification problems.
imbalance-correctionlearnersensemble-learningclassificationr-package
PhilippPro/CranDownloads
Mar 2017 - Oct 2022
Contributions:11 pushes, 1 branch in 5 years 7 months
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.