Ole Behre

M.Sc. Data Science | Forecasting & Applied ML
Seeking applied ML & research internships | Netherlands & Antwerp | Early 2027

Selected Projects

[ 01: EPEX Day-Ahead Price Forecasting ]

Probabilistic day-ahead electricity price forecasting on EPEX SPOT DE/LU. TabPFN-TS + LightGBM + CQR vs. zero-shot Chronos-Bolt, with news sentiment ablation.

-> View Details
[ 02: Probabilistic Wind Power Forecasting ]

Spatial, probabilistic wind power generation forecasting for Germany. Spatial clustering + LightGBM quantile regression.

-> View Details
[ 03: Structure-Aware Graph Mixup ]

Blending training examples reliably helps image models and reliably fails on graphs. We measured what the blending destroys, and tested whether protecting it helps.

-> View Details
[ 04: Bike Traffic Forecasting ]

Comparative analysis of point forecast models on urban mobility signals.

-> View Details
[ 05: Robustness of LLM Reasoning ]

Adversarial stress-testing of LLM robustness. Created novel multilingual, adversarial benchmark.

-> View Details
View on GitHub

Deep Dives

[+]
In-Context Forecasting in Supply Chains: Evaluating the Promise and Limits of Tabular Foundation Models
TabPFN Demand Forecasting In-Context Learning
| 2026

Evaluating the limits and promise of Tabular Prior-Data Fitted Networks (TabPFN) and ApolloPFN for zero-shot demand forecasting in data-scarce supply chains, highlighting trend extrapolation and context window bottlenecks.

-> Read Paper (PDF)
[+]
Deep Learning for Bearing Predictive Maintenance: A Review of Four Different Architectures
Deep Learning Predictive Maintenance LSTM
| 2026

Critically analyzing four deep learning approaches to bearing remaining useful life (RUL) prediction (DNN, Stacked Denoising Autoencoder, CNN-based transfer learning, and LSTM-fusion) and uncovering structural data leakage issues in the baseline evaluation.

-> Read Paper (PDF)
[+]
Red Teaming LLMs: Gender Bias in AI-Generated Parenting Advice
LLMs Red Teaming Gender Bias
| 2026

Auditing implicit gender bias in frontier LLMs within the parenting and child development advice domain using identity swapping red teaming to investigate allocative and representational harms.

-> Read Paper (PDF)

Education

Exchange Semester, M.Sc. Data Science Sep 2026 – Jan 2027
National Taiwan University (NTU) | Taipei, Taiwan  [current]
  • Courses: Time Series Analytics; Robot Perception and Learning (Reinforcement Learning); Optimization & AI in IoT.
  • Scholarship: Baden-Württemberg-STIPENDIUM by Baden-Württemberg Stiftung.
M.Sc. Data Science 2025 – 2028 (Expected)
University of Mannheim | Grade: 1.3
  • Focus: Machine Learning, Data Integration, Deep Learning, Large Scale Data Management, Applications of AI in Industry.
  • Scholarship: Deutschlandstipendium, awarded 2026.
B.Sc. Information Systems (Wirtschaftsinformatik) 2021 – 2025
University of Mannheim | Grade: 1.6
  • Thesis: "Multilingual, Adversarial Math Word Problems: Testing the Robustness of Large Language Models" (Grade: 1.0).
  • Relevant Coursework: IT-Security, Artificial Intelligence, Data-Driven Analysis.

Selected Experience

Working Student, Software Engineering Jul 2025 – Jul 2026
FORRS | Frankfurt am Main
  • Automated trading-desk workflows and data integrations for high-frequency short-term markets, focusing on reliability and operational observability.
  • Contributed to the architecture of a cloud-based market data platform ingesting and normalising high-volume time-series.
  • Built ETL pipelines and REST APIs integrating external real-time data feeds.
Research Assistant Jul 2025 – Oct 2025
University of Mannheim | Data and Web Science Group (DWS)
  • Ran LLM benchmark suites on Slurm-scheduled HPC clusters.
  • Built custom vLLM inference pipelines with intervention hooks to extract and analyse redundancy patterns in the reasoning traces of frontier models (e.g. Deepseek-R1).
  • Conducted quantitative evaluations of inference-time interventions, analyzing the stability and brittleness of Chain-of-Thought (CoT) prompting.
Working Student, Software Engineering (Backend) Sep 2023 – Jan 2025
FORRS | Frankfurt am Main
  • Developed backend services in Java/Quarkus for the MDM cloud platform.
  • Improved REST endpoint performance for high-volume time-series queries.
Working Student, Consulting & Communications Mar 2022 – Dec 2023
FORRS | Frankfurt / Munich (Remote)
  • Conducted data analysis and market research to support consulting projects across the energy trading value chain.
  • Produced and organized a targeted podcast series exploring the technical and business intersection of Data Science and the energy industry.
Member Mar 2023 – Present
STADS e.V. (Student Association for Data Analytics)
  • Website maintenance and infrastructure restructuring.
  • Automation of internal association processes.
  • Trying to get people to join the STADS Running Club ;)

Technical Specifications

Languages Python, Java, SQL, HTML/CSS
Methods Probabilistic forecasting, quantile regression, conformal prediction, time-series modeling
ML Libraries scikit-learn, LightGBM, CatBoost, pandas, NumPy
Deep Learning & LLMs PyTorch, Transformers, Hugging Face, vLLM, lm-eval
Backend & APIs FastAPI, PostgreSQL, REST, WebSockets, Quarkus, ETL
Infrastructure Docker, Linux, Git, Slurm/HPC
Ways of Working Agile/Scrum, Jira, Confluence, LLM-assisted development
Spoken Languages German (native), English (TOEFL 117/120), Mandarin (learning)

Tinkering

[ FlashChinese 快 ]

Built this to learn Mandarin in Taipei. Type a sentence and get traditional characters, pinyin and a word-by-word breakdown, or draw characters by hand and have them recognised. A few friends use it now too.

-> View Details
[ Paperdolmetscher ]

A birthday present for my sister, who studies midwifery: English papers turned into German, paragraph by paragraph, with a glossary that stays consistent across papers.

-> View Details
[ querying live weather data... ]
Animation of a wind park representing renewable energy interest.