Hey there, I'm Georgios Douzas! I'm a machine learning researcher and software engineer. If you're interested, feel free to take a look at my CV or personal blog.

A list of my personal projects:

• geometric-smote: An implementation of the Geometric-SMOTE algorithm. Compatible with scikit-learn and imbalanced-learn libraries.
• cluster-over-sampling: A general interface for clustering based over-sampling algorithms. It allows to create oversampling algorithms as combinations of clusterers and oversamplers. Compatible with scikit-learn and imbalanced-learn libraries.
• sports-betting: A collection of tools that makes it easy to create machine learning models for sports betting and evaluate their performance. Compatible with scikit-learn.
• sage-physics: A Python package to create and simulate physics models. It aims to provide a unified interface for various physics models. It is based on SageMath.
• copier-pdm-nox: Copier template for Python projects managed by PDM with the help of Nox.

• Geometric SMOTE for regression. Expert Systems with Applications.
• Improving the quality of predictive models in small data GSDOT: A new algorithm for generating synthetic data. PLOS ONE.
• G-SOMO: An oversampling approach based on self-organized maps and geometric SMOTE, Expert Systems with Applications.
• Increasing the effectiveness of active learning: Introducing artificial data generation in active learning for land use/land cover classification. Remote Sensing.
• Improving imbalanced land cover classification with k-means smote: Detecting and oversampling distinctive minority spectral signatures. Information.
• Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE. Information Sciences.
• Imbalanced learning in land cover classification: Improving minority classes’ prediction accuracy using the geometric SMOTE algorithm. Remote Sensing.
• Effective data generation for imbalanced learning using conditional generative adversarial networks. Expert Systems with Applications.
• Improving imbalanced learning through a heuristic oversampling method based on k-means and SMOTE. Information Sciences.
• Self-Organizing Map Oversampling (SOMO) for imbalanced data set learning. Expert Systems with Applications
• Coset space dimensional reduction and Wilson flux breaking of ten-dimensional N=1, E8 gauge theory. The European Physical Journal C.
• Coset space dimensional reduction and classification of semi-realistic particle physics models. Progress of Physics.