Overview

The repository contains the published work of the NOVA IMS Innovation and Analytics Lab.

Publications

A list of published papers and work in progress.

Published work

• Geometric SMOTE for regression
• Improving the quality of predictive models in small data GSDOT: A new algorithm for generating synthetic data
• G-SOMO: An oversampling approach based on self-organized maps and geometric SMOTE
• Increasing the effectiveness of active learning: Introducing artificial data generation in active learning for land use/land cover classification
• Improving imbalanced land cover classification with k-means smote: Detecting and oversampling distinctive minority spectral signatures
• Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE
• Imbalanced learning in land cover classification: Improving minority classes’ prediction accuracy using the geometric SMOTE algorithm
• Effective data generation for imbalanced learning using conditional generative adversarial networks
• Improving imbalanced learning through a heuristic oversampling method based on k-means and SMOTE
• Self-Organizing Map Oversampling (SOMO) for imbalanced data set learning
• Genetic Programming for Offline Reinforcement Learning

Work in progress

• Imbalanced text classification using Geometric SMOTE oversampling algorithm
• cluster-over-sampling: A Python package for clustering-based oversampling
• geometric-smote: A package for flexible and efficient oversampling
• Intraday trading via Deep Reinforcement Learning and technical indicators