Skip to content
View ggelissen's full-sized avatar
  • Technical University of Munich
  • Munich, Germany
  • LinkedIn in/ggelissen

Highlights

  • Pro

Block or report ggelissen

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ggelissen/README.md

Gabriël Gelissen

Applied Mathematics MSc student at the Technical University of Munich, focused on quantitative research, statistical learning, time-series modelling, and portfolio risk.

I build research-oriented software at the intersection of dependence modelling, machine learning, optimisation, and financial decision-making. I care about leakage-free evaluation, reproducibility, realistic constraints, and conclusions that match the available evidence.

Selected work

Project What it demonstrates
Dynamic portfolio selection with vine copulas Time-varying D-vines, AR-GARCH marginals, synthetic-data validation, recurrent TD3, CVaR-aware allocation, and controlled out-of-sample evaluation
Copula estimation research Monte Carlo research on marginal uncertainty, copula-family effects, sample size, bias, variance, and estimation error
Statistical arbitrage modelling Statistical arbitrage, cointegration, copula-based signals, volatility targeting, backtesting, and risk analytics
AERIS aircraft design Multidisciplinary scientific computing across sizing, optimisation, aerodynamics, structures, propulsion, and flight performance in a large team project

Current interests

  • Dependence and tail-risk modelling
  • Quantitative portfolio construction and risk management
  • Statistical and machine-learning methods for time series
  • Robust backtesting, model validation, and reproducible research
  • Scientific software for high-dimensional optimisation

Tools

Python · R · PyTorch · TensorFlow/Keras · pandas · NumPy · SciPy · Git

You can find my professional background on LinkedIn.

Pinned Loading

  1. vine-copula-rl-portfolio vine-copula-rl-portfolio Public

    Research implementation of leakage-aware dynamic portfolio allocation using time-varying D-vines, AR-GARCH marginals and recurrent TD3 under CVaR and trading constraints.

    R

  2. copula-research copula-research Public

    Monte Carlo research on how unknown marginal distributions and simplifying assumptions affect copula estimation error across families and sample sizes.

    R 1

  3. statistical-arbitrage-modelling statistical-arbitrage-modelling Public

    Research prototypes for statistical arbitrage, cointegration, copula signals, volatility targeting, portfolio backtesting and risk analytics in Python.

    Python

  4. aeris-aircraft-design aeris-aircraft-design Public

    Team-built conceptual aircraft-design framework integrating sizing, aerodynamics, structures, propulsion, flight performance, optimisation and sensitivity analysis.

    Gnuplot 2