Dustin Brunner

Dustin Brunner

MSc CS @ ETH Zürich

View My GitHub Profile

Contents:

Contents:

Minimalistic — Theme by vaibhavvikas

Hey There!

I’m a Master’s student in Computer Science at ETH Zürich, specializing in Machine Intelligence and Data Management. My expertise lies at the intersection of computer science and statistics, where I apply my skills in machine learning, and big data technologies to solve real-world problems and create effective solutions.

I have practical experience in data engineering, machine learning, and forecasting, including contributions to the Darts forecasting library and developing tools for industries such as logistics and energy.

Feel free to connect if you’re interested in collaborating! I’m eager to explore new challenges, particularly in Data Science, Quantitative Finance, or Big Data Engineering roles.

LinkedIn GitHub Google Scholar

Skills

Programming Languages
Python • R • C++ • Java • Typescript
Frameworks & Libraries
PyTorch • NumPy • Pandas • Optuna • Plotly • Hugging Face • tidyverse
Data Management
SQL • Spark • Hadoop • HBase • MongoDB • Neo4j
Other Tools
Git • Docker • Bash • MLOps • CI/CD • GitHub Actions • Notion • Jira
Focus Areas
Forecasting • Visualization • Explainability • Causal Inference • Natural Language Processing (NLP) • Graph Neural Networks (GNNs)
Languages
German (Native) • English (Proficient) • French (Elementary)

Education

ETH Zürich
Master of Science in Computer Science (2022 - 2024)
Major: Machine Intelligence | Minor: Data Management
GPA: 5.46 / 6.0

ETH Zürich
Bachelor of Science in Computer Science (2018 - 2021)

Experience

Unit8 | Data Scientist

Sep 2021 - Aug 2022 | Zürich, Switzerland

Projects

Recommender Systems for Swiss Politics

Master’s Thesis (Feb 2024 - Aug 2024)
Paper (confidential - under submission) | Smartvote

Identified 11 vulnerabilities in the swiss voting advice application Smartvote with some allowing for more than 3.5x visibility gains for individual parties. Proposed 10 mitigations to significantly reduce or eliminate these vulnerabilities. Findings are being adopted in Smartvote’s redesign for the next elections.

Technologies: Python, Pandas, D-Tale, SciPy, Optuna, Plotly, LaTex, Notion

RSFP Manipulation

DataComp Challenge

Semester Project (Sep 2023 - Dec 2023)
Report | DataComp Website

Ranked 4th out of 12 teams in the small track of the DataComp Challenge, an ML benchmark where the goal was to filter a CommonCrawl image-text dataset to train a CLIP model evaluated on 38 zero-shot downstream tasks, using a combination of cross-modality filtering and content alignment.

Technologies: Python, PyTorch Lightning, SLURM (Cluster), CLIP (Contrastive Language-Image Pretraining)

DataComp Workflow

BasketXplainer

Interactive ML Project (Feb 2023 - Jul 2023)
Interactive Demo | Paper | GitHub

Developed an interactive dashboard to predict basketball game outcomes based on in-game stats and explain predictions using SHAP values. Users could modify team statistics to explore what-if scenarios.

Technologies: Python, scikit-learn, SHAP, Flask, Javascript, React, Gitlab Pipelines

BasketXplainer Prediction

Darts Forecasting Library

Contributor (Sep 2021 - Aug 2022)
Documentation | Paper | GitHub

Core contributor to the open-source time series forecasting library Darts by Unit8. Optimized the most popular regression forecasting models by vectorizing computations achieving a speedup of up to 400x.

Technologies: Python, PyTorch, scikit-learn, Matplotlib, Git, GitHub Actions

pip install darts

Darts Logo

Distance Preserving Graph Embedding

Bachelor’s Thesis (Feb 2021 - Aug 2021)
Report

Developed a model that enables constant-time approximate shortest path distance queries on road networks, achieving an average mean relative error of less than 10%.

Technologies: Python, NetworkX, PyTorch Geometric, (Hyperbolic) Graph Convolutional Networks ((H)GCNs)

Winterthur
Winterthur, Switzerland
Surat
Surat, India
Dongguan
Dongguan, China

Achievements

Advanced Machine Learning Projects (2023)
Achieved 1st place twice and 7th place once out of over 100 teams in practical projects for the Advanced Machine Learning course at ETH Zürich. The course was competitively graded, meaning that grades were interpolated between the passing baseline score (grade 4) and the best-performing team (grade 6).

  1. Tabular Regression: Predicting age from brain scans — 1st place
  2. Timeseries Classification: Classifying heart rhythm patterns from ECG signals — 7th place
  3. Video Segmentation: Segmentation of mitral valve from ECG videos — 1st place

Mathematics Kangaroo Switzerland (2015)
Ranked 40th out of 5,787 students (top 0.7%) in Switzerland’s largest mathematics competition, which tests problem-solving and analytical skills through a series of math challenges.

Hobbies