Jesper Armouti-Hansen
Pixel-art portrait of Jesper Armouti-Hansen

Curriculum vitae

Jesper Armouti-Hansen

Data scientist with an economics PhD and a decade of applied data work. I build statistical and machine-learning models on structured data, and assess when their output is reliable enough to act on.

Download PDF Email LinkedIn

Experience

Apr. 2026 – present · Cologne, Germany

Data Scientist, AXA Konzern AG

  • Work on a production document-understanding pipeline that segments stacks of scanned pages into documents (boundary detection) and classifies each — hundreds of thousands of stacks per month — flagging low-confidence cases for human review.
  • Built document-class-specific confidence thresholds that automate more documents while holding at least 95% precision per class, cutting manual review by around 30% in production.
  • Researching pipeline upgrades: an LLM post-processing step for frequently-confused class pairs, and a single vision-language model (Qwen3.5-4B) to replace the existing two-stage BERT+CLIP and RNN stack.

Jan. 2022 – Mar. 2026 · Bonn, Germany

Postdoctoral Researcher in Economics, University of Bonn

  • Ran empirical and computational economics research — statistical and econometric modeling, machine-learning benchmarking, and partial-identification with simulation.
  • Developed theoretical models and built reproducible analysis pipelines in Python and R; benchmarked economic theories against machine-learning models to quantify how much predictable variation each captures.
  • Published peer-reviewed research and presented at international conferences.

Dec. 2015 – Dec. 2021 · Cologne, Germany

Research Assistant in Economics, University of Cologne

  • Conducted PhD research in microeconomic theory and experimental economics — decision-theory and contract-theory modeling, with empirical analysis of experimental data.

Dec. 2014 – May 2015 · Neu Isenburg, Germany

Intern, AirPlus International

  • Built VBA tools for data management and process automation.

Strengths

Statistical modeling, model evaluation, and forecasting, backed by an economics PhD.

Model evaluation

Accuracy, calibration, and error-pattern checks that decide where a model can run on its own and where it needs review.

Statistical & econometric modeling

Statistical and econometric models, built and estimated on structured data, with a clear read on how much of the variation they actually capture.

Machine learning on structured data

Machine learning on tabular data (gradient boosting, regularized models, and the like), always benchmarked against a simple baseline so the added complexity has to earn it.

Reproducible code

Version-controlled, tested code in Python, SQL, and R. The economics training is the edge on the harder part: telling a real effect from noise.

Skills

The concrete stack: languages, libraries, methods, and tools.

Programming languages
PythonRSQLStataTypeScript
Python stack
NumPypandasSciPyscikit-learnstatsmodelsPyTorchXGBoost / LightGBMGeoPandas
Methods
Statistical modelingEconometricsMachine learningModel evaluation & calibrationForecastingExperiment & A/B analysisSimulationFine-tuningRetrieval / RAG
Tools & workflow
GitGitHub ActionsDockerpytestuvpixiJupyterLabLinuxLaTeX
Languages
EnglishGermanDanish

Education

2015 – 2021 · Cologne, Germany

PhD in Economics (Dr. rer. pol.)

University of Cologne. Summa cum laude. Focus on microeconomics, statistics, and econometrics.

2012 – 2014 · Mainz, Germany

MSc International Economics and Public Policy

University of Mainz. GPA 1.6.

2008 – 2012 · Copenhagen, Denmark

BA Financial Management and Services

Copenhagen Business Academy

2010 · Nicosia, Cyprus

Exchange semester

European University of Cyprus

Teaching & supervision

University lecturer and tutor in applied, behavioral, personnel, and organizational economics. Supervised 60+ bachelor's and master's theses along the way.