Skip to content
View marieltv's full-sized avatar

Block or report marieltv

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
marieltv/README.md

Data Scientist | Quantitative Finance & Machine Learning | Python.

Bachelor’s Degree — Economics (Economic Cybernetics)
Master’s Degree — Computer Science

📫 Contact me


🛠 Skills & Technologies

📊 Quantitative & Financial

scipy scikit-learn


🐍 Programming & Data

Python Pandas NumPy SQL


🤖 Machine Learning & Computer Vision

PyTorch OpenCV YOLO


📈 Visualisation & Analysis

Matplotlib Seaborn


⚙️ Tools & Environment

Git Kaggle Google%20Colab Plotly Streamlit


🚀 Selected Projects

Portfolio Optimisation — Out-of-Sample Evaluation
Rolling walk-forward backtest comparing Equal Weight, Minimum Variance, Risk Parity, and Regularised Max Sharpe on US defence equities. Includes predicted vs actual Sharpe/Sortino analysis, Ledoit-Wolf and James-Stein shrinkage estimators, and an interactive Streamlit dashboard.
Python · scipy · pandas · scikit-learn · Streamlit · Plotly · GitHub Actions

YOLOv8 Segmentation Optimisation
Hyperparameter optimisation, cross-validation, custom loss functions, GPU-aware training.
PyTorch · OpenCV · YOLO


🌱 Outside of Work

  • Health, fitness, and well-being 🌿
  • Classical music and the arts 🎻

Popular repositories Loading

  1. yolov8-seg-modified yolov8-seg-modified Public

    Ships Detection & Segmentation System with Multi-Objective Optimization

    Python

  2. marieltv marieltv Public

  3. portfolio_optimization portfolio_optimization Public

    Walk-forward portfolio optimisation backtest comparing four allocation strategies with predicted vs actual risk analysis and an interactive Streamlit dashboard.

    Python