Jan Stüwe
Data Scientist

Internship – Data Science

BMW AG, München

02/2025 – 04/2025

I worked on clustering and statistical analysis of automotive data, utilizing partitioning, hierarchical, and density-based clustering techniques to extract meaningful insights. My focus was on evaluating the models' performance using both internal and external metrics to ensure robustness and accuracy. To ensure data representativeness, I applied a stratified sampling strategy, which helped maintain the integrity of the dataset. Additionally, I conducted rigorous descriptive and inferential statistical analysis to validate the results and ensure their statistical reliability, providing confidence in the conclusions drawn from the data.

Neural-Network supported 3DVar with Lorenz’63

In this project, we implemented a neural-network-supported 3DVar data assimilation pipeline on the chaotic Lorenz ’63 system. We generated a synthetic twin experiment and computed innovations and 3DVar increments to establish a strong classical baseline. On top of that, we trained a compact MLP (ReLU, Adam, early stopping) to predict analysis increments directly from the background state and observations, and also evaluated a hybrid scheme that blends the learned increment with the 3DVar update. Evaluation included an 80/20 train–validation split, Monte-Carlo studies across multiple observation-noise levels, and a partial-observations setting. Across settings, the learned model consistently reduced mean L2/RMSE versus standard 3DVar. Overall, the approach demonstrated robust improvements in state estimation over classical 3DVar.

Time-to-sell Prediction together with Audi

As part of a team of four, I worked on a project for Audi focused on predicting the time it takes to sell cars. We developed a deep learning model that accurately predicted the timespan, achieving a margin of error of just 9 days, significantly outperforming the baseline of approximately 20 days. To ensure the predictions were interpretable, we also utilized a Generalized Additive Model (GAM), which allowed us to gain valuable insights into the key factors influencing the sales times. The project placed a strong emphasis on handling high-dimensional data and performing comprehensive feature preprocessing to ensure optimal model performance. Our team presented our findings multiple times at Audi, demonstrating the model’s effectiveness and impact. The project was graded with a top score of 1.0.

Fake News Classification

In my second semester, I worked on a project focused on classifying news as fake or true of this Kaggle Fake and Real News Dataset, utilizing both classical machine learning classification methods and modern deep learning approaches. The project required extensive data preprocessing, feature engineering, and careful model evaluation to ensure accuracy and robustness. By applying a combination of traditional techniques and advanced neural networks, I was able to achieve highly reliable results. The final model achieved an accuracy of approximately 99%, demonstrating strong generalization across both classes. The project was graded with the highest possible score of 1.0.

Portfolio Website

I designed and built my personal portfolio website with a lightweight, static stack: HTML, CSS, and JavaScript. The UI includes quality-of-life controls such as a white mode and an option to deactivate the animated particles background for improved readability and reduced motion. Content is organized into clear sections (Work Experience, Projects, Education, Skills, Socials), with a downloadable resume and a simple contact form, all wrapped in a responsive layout that works smoothly across devices. I kept dependencies minimal, optimized images and icons, and used semantic markup to keep the site fast and maintainable. Icons are sourced from RemixIcon, Font Awesome, and Devicon, and the whole site is built and styled by me end-to-end.