Researchers have developed new methods to address data imbalance in regression tasks, a common issue that biases model performance, especially when predicting rare events. The study introduces novel sampling techniques, cSMOGN and crbSMOGN, alongside density-distance and density-ratio relevance functions to better integrate data frequency with domain-specific preferences. Evaluations on numerous synthetic and real-world datasets using neural networks, XGBoosting, and Random Forest models indicate that while most strategies improve performance on rare samples, they often degrade performance on frequent ones. The proposed crbSMOGN technique, particularly with neural networks, demonstrated superior performance over existing state-of-the-art methods. AI
IMPACT Introduces new techniques to improve the reliability of regression models in scenarios with imbalanced datasets.
RANK_REASON Research paper detailing novel methods for data imbalance mitigation in regression. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
